Comparing Google Lens Recognition Accuracy with Other Plant

Recognition Apps

Zhanna I. Bilyk

1 a

, Yevhenii B. Shapovalov

1 b

, Viktor B. Shapovalov

1 c

, Anna P. Megalinska

2 d

Sergey O. Zhadan

3 e

, Fabian Andruszkiewicz

4 f

, Agnieszka Dołha

nczuk-

odka

4 g

and

Pavlo D. Antonenko

5 h

National Center “Junior Academy of Sciences of Ukraine”, 38-44 Degtyarivska Str., Kyiv, 04119, Ukraine

National Dragomanov Pedagogical University, 9 Pyrohova Str., Kyiv, 01601, Ukraine

Individual Entrepreneur “Dyba”, Kiev, 03035, Ukraine

Uniwersytet Opolski, 11a Kopernika pl., Opole, 45-040, Poland

College of Education, University of Florida, PO Box 117042, Gainesville, FL 32611-7044, USA

Keywords:

Mobile Application, STEM-Classes, Augmented Reality, Plant Identiﬁcation, Google Lens.

Abstract:

Motivation students by providing personalized researches and using IT during classes is relevant in the frame

of STEM approach of education. However, there is a lack of researches devoted to the justiﬁcation of these

approaches. The aim of the research is justifying of the choosing of AR-plant recognition application choosing

to provide personalized during both, educational process at school and extracurricular activities. All apps

were analyzed and characterized by all processes of interaction of the app with the user. In addition, social

environments of the apps and their usage during extracurricular activities described. The didactics of usage of

AR-recognition apps on biology classes have been described. To provide usability analysis, a survey of experts

on digital education on installation simplicity, level of friendliness of the interface, and correctness of picture

processing was conducted. To evaluate the rationality of usage, apps were analyzed on the accuracy of plants

recognition of the “Dneprovskiy district of Kiev” list. It is proven that Google Lens is most recommended to

use. Taking to account results of the analysis, as alternative Seek or Flora Incognita; however, these apps were

characterized by lower accuracy.

1 INTRODUCTION

To date, the introduction of a mobile phone into the

educational process is a modern instrument, which

provides achieving better results. The usage of a mo-

bile phone during classes provides visualization of

educational material, involving students in research,

which increases students’ motivation for learning

(Mart

ın-Guti

errez et al., 2015; Kinateder et al., 2014).

Mobile phone applications compared to computer ap-

https://orcid.org/0000-0002-2092-5241

https://orcid.org/0000-0003-3732-9486

https://orcid.org/0000-0001-6315-649X

https://orcid.org/0000-0001-8662-8584

https://orcid.org/0000-0002-7493-2180

https://orcid.org/0000-0001-5318-3793

https://orcid.org/0000-0002-9654-4111

https://orcid.org/0000-0001-8565-123X

proaches are characterized by the most promising ad-

vantages including mobility of usage, possibility to

use both internal and external sensors (not commonly

used). The modern educational directions include

personalization and research process which may be

achieved by using mobile phones (Marienko et al.,

2020). However, it was proved that not certain el-

ements of education but a general didactic approach

led to signiﬁcant effect (Shapovalov et al., 2020b).

The main concept during which the mobile approach

relevant to use is STEM/STEAM/STREAM technol-

ogy. Those methods include using of both, research

(scientiﬁc) and engineering methods. To improve the

efﬁciency of them, use of computer software or mo-

bile applications can be used.

The role of information technology in the learning

process is widely described (Kinateder et al., 2014;

Park, 2011; Clark and Ernst, 2008; Shapovalov et al.,

Bilyk, Z., Shapovalov, Y., Shapovalov, V., Megalinska, A., Zhadan, S., Andruszkiewicz, F., Dołha

nczuk-

Sródka, A. and Antonenko, P.

Comparing Google Lens Recognition Accuracy with Other Plant Recognition Apps.

DOI: 10.5220/0010928000003364

In Proceedings of the 1st Symposium on Advances in Educational Technology (AET 2020) - Volume 2, pages 20-33

ISBN: 978-989-758-558-6

2019; Dziabenko and Budnyk, 2019; Kapici et al.,

2019; Devi and Rav, 2018).

1.1 Types of Software Which Can Be

Used during Education

All software that can be used during the learning pro-

cess in the application of STEM technology can be di-

vided into desktop applications, mobile applications,

and web-oriented technologies. The most perspective

of information and communication technology (ITC)

to use is augmented reality (Mart

ın-Guti

errez et al.,

2015; Kinateder et al., 2014; Marienko et al., 2020;

Shapovalov et al., 2018; Agustina et al., 2019), vir-

tual reality (Kinateder et al., 2014; Potkonjak et al.,

2016; Joiner, 2018; Lee and Wong, 2014; Sala, 2014;

Hussein and N

atterdal, 2015; Zantua, 2017; Antoni-

etti et al., 2001; Park, 2011), providing of digital envi-

ronments of education, including computer modeling

(Sarabando et al., 2014; Sahin, 2006; Sifuna, 2016;

Khine, 2018; Clark and Ernst, 2008), providing of

centralized educational networks (Shapovalov et al.,

2019; Stryzhak et al., 2019), mobile-based education

(Modlo et al., 2019), modeling environments (Dzi-

abenko and Budnyk, 2019; Jong et al., 2014; de Jong,

2019; Kapici et al., 2019) providing of education visu-

alization by including YouTube videos (Chorna et al.,

2019), 3D modeling and printing, etc. Comparison

of the most used in the education process software is

presented in table 1.

So, using of mobile phone apps during educa-

tional process is characterized by arrays of advan-

tages such as multi-capabilities, interaction with stu-

dents in their research and visualization on the edu-

cational process. Detailly, mobile apps can be classi-

ﬁed as measuring apps, analyzing apps, image recog-

nition and classiﬁcation apps, course platforms, VR

and AR-based apps. Based on functions of apps, they

can be deviated into the following categories:

• training (course) platforms;

• measuring apps;

• video analysis apps;

• applications that analyze images and classify

them;

• augmented and virtual reality (AR and VR) apps.

Comparison of different mobile apps categories is

shown in table 2.

Apps-identiﬁers characterized by high potential

to especially in biology classes due possibility to

provide personalized researches. Today, there is a

range of mobile applications that identify wildlife.

Such apps are insects- (for example, Insect iden-

tiﬁer Photo), animals- (Dog Scanner), mushrooms

(Fungus) and plants-identiﬁcatory (Flora Incognita,

PlantSnap, Picture This). Some apps provide identiﬁ-

cation of few type nature (both, plants and animals),

for example Seek. In our opinion, most promising are

applications that provide analyzing of the static ob-

jects of the nature (plants and mushrooms). It is due to

lower requirements to the camera. So, they don’t re-

quire high-expensive smartphones and it can be used

widely during the educational process, almost in all

schools.

1.2 The Problem of Plants Identiﬁcation

There are about 27,000 species of ﬂora in Ukraine.

Such biodiversity requires detailed description and

study. Also, natural conditions are constantly chang-

ing, and this causes changes in the species composi-

tion of biocenosis. Both aspects indicate that there is

a problem with plant identiﬁcation. One of the basic

principles of pedagogy is the principle of a nature ex-

periment. For a modern child, a mobile phone with

Internet access is its natural environment. So, train-

ing should be carried out in an environment, where

the mobile phone should become a full-ﬂedged learn-

ing tool.

Some apps can be installed on the student’s mobile

phone for free to determine the species of plants, their

morphology, the range of distribution, and more.

There are about 10 applications that can be used to

identify the plants. Most common of them are LeafS-

nap, Seek, PlantNet, Flora Incognita, PlantSnap, Pic-

ture This, Florist-X (in Russian), What is a ﬂower

(in Russian), Manager of houseplants (in Russian).

These applications can be divided into three gro plant

identiﬁers that can analyze photos (Google Lens, for

example, PlanNet, Flora Incognita, PlantSnap, Pic-

ture This. ups, such as:

• plant identiﬁers that can analyze photos (Google

Lens, for example, PlanNet, Flora Incognita,

PlantSnap, Picture This.

• plant classiﬁcation provides the possibility to

identify plants manually. The plant’s classiﬁca-

tory commonly contains pictures and information

about plant kind. But the quality of analysis, in

this case, will depend on the user’s knowledge

and skills which may be hard for both teachers

and students. Their use in biology lessons within

the STEM approach has considerable potential

because it allows to lean the plant morphology.

However, its efﬁciency depends on the knowledge

of user which may be lacked in case of pupils (for

example, Florist-X and What is a ﬂower).

Comparing Google Lens Recognition Accuracy with Other Plant Recognition Apps

Table 1: Comparison of the most used in the education process software.

Type Web-oriented Mobile applications Desktop applications

Installation Not required From ofﬁcial stores or using

application ﬁle

From ofﬁcial stores or installation

ﬁles

General re-

quirements

Compatible Internet browser

for all features support

Compatible version of An-

droid, iOS or another mobile

operating system

Compatible version of Win-

dows/macOS/Linux or another

desktop operating system

Facilities Modeling, calculation, visu-

alization, video presenting

Modeling, calculation, visual-

ization, video presenting, AR,

measuring using both internal

and external sensors, photo

analysis, AR, VR

Modeling, calculation, visualiza-

tion, video presenting, using ad-

ditional external sensors

Main

advantages

Cross-platforming, no in-

stallation required, low de-

vice space usage

Huge possibilities, mobility

of usage

Stability and variation of applica-

tions

Main disad-

vantages

Limited opportunities, may

not start correctly depending

on the platform, lack of indi-

vidualization

Needs technical updates

which may be expensive

(in two-three years may be

required to buy new phone)

Lack of individualization, the

lesser effect of increasing motiva-

tion during STEM-education

Table 2: Comparison of the most used in the education process software.

Type of application Description Examples

Education platforms These platforms allow the teacher to create

instructional content, communicate with stu-

dents, give them assignments and check them

out automatically

Google Classroom, Prometheus,

Coursera, Microsoft Ofﬁce 365

for Education

Measuring applications These sensors and their software are already

built into mobile phones

Measure, AR-ruler, Smart Mea-

sure, Lux-meter, Accelerometer,

Magnet Field Meter

Image analysis apps It allows you to measure distances, angles,

perimeters, areas, and calculate with this data.

ImageMeter

Image recognizing and

it’s classiﬁcation appli-

cations that analyze im-

ages and classify them

These mobile applications allow you to iden-

tify species of plants and animals using photos

Identiﬁcation, Mushroom, Iden-

tify, Shazam, Dog Scanner, Iden-

tify

VR and AR-based apps Allow virtual travel, get a spatial image of the

training material.

Minecraft Earth, IKEA Place,

Ideoﬁt, Lego Hidden Side

• plants-care apps that remind water of the plant or

change the soil, which characterized by the lower

potential compared to other types of application

(for example Manager of houseplants).

Taking into account all advantages of plant iden-

tiﬁers, they were used as an object of the research. It

was proven that Google Lens provides high efﬁciency

in plant type and species identiﬁcation (Shapovalov

et al., 2020a). Google lens can provide analysis of

real-life objects in AR and provide additional infor-

mation using neural network algorithms. A few arti-

cles have devoted to Google Lens that proves its ac-

tuality to use (du Plessis, 2015; Syawaldi et al., 2019;

Devi and Rav, 2018). However, some apps-identiﬁers

may be more specialized and may provide better efﬁ-

ciency of the identiﬁcation.

Despite the great specialization of other applica-

tions, hypothesize the research is that Google Lens

is the best plant analyzer due to larger database, bet-

ter algorithmic of analyzing and teaching of AI using

Google crowdsource app (500 000+ installation).

Therefore, the purpose of this article is to analyze

existing applications, that can be used in teaching bi-

ology both in the classroom and in the ﬁeld.

2 METHODS OF ANALYZING

To provide an analysis of the usability of applications

related to plant identiﬁcation, a survey of experts on

AET 2020 - Symposium on Advances in Educational Technology

digital didactics was provided. The main criteria were

installation simplicity, level of friendliness of the in-

terface, correctness of picture processing. Each crite-

rion was evaluated from 0 to 5 (as higher than better).

Those applications which were characterized by aver-

age evaluation more than 4 were used to further anal-

ysis on quality of identiﬁcation due taken to account

fact usage of the application during the educational

process, where it will be used by students and teach-

ers, both potentially with not the highest level of ICT

competence.

Analysis of quality of identiﬁcation was provided

by a simpliﬁed method compared to our previous re-

search due aim of this paper to obtain a general state

on application plant identiﬁcation accuracy. To pro-

vide it, 350 images from the list of plants of the “Dne-

provskiy district of Kiev” were taken to provide anal-

ysis. The key from the “Dneprovskiy district of Kiev”

plant classiﬁcation was used as control. To analyze

the data, tables with names of the plant as lines and as

names of app in columns has created. For each suc-

cessful identiﬁcation at the intersections “1” has put

and for each unsuccessful “0” has put (see an exam-

ple in table 3).

Table 3: Example of the table of apps analyzing.

The name of the plant

Flora

Incognita

PlantNet

Prunus armeniaca (Apricot) 0 0

Jasione montana 0 1

Ageratum houstonianum 0 1

Chaenomeles japonica 0 0

Amaranthus 1 0

Ambrosia artemisiifolia 0 1

Amorpha fruticosa 0 0

Anemo 1 1

Anemonoides ranunculoides 1 0

Anisanthus tectorum 0 0

Finally, all obtained results, including both, gen-

eral usability evaluation (survey) and results on iden-

tiﬁcation quality were compared with results on

Google Lens to summarize information and achieve

a general and ﬁnal state in this ﬁeld.

3 RESULTS

3.1 Analysis of the Interaction with

Apps

General characteristics of the apps. The apps

databases are signiﬁcantly differing. The lowest num-

ber of plants in database is included in Flora Incog-

nita (4800 species) and the highest is included in

PlantSnap (585,000 species).

In additions, the apps databases differ by pres-

ence of species based on geographical locations.

For example, Flora Incognita’s database is very lim-

ited geographically and contains only German ﬂora;

Opposite, PlantNet’s data is geographically very

wide and contains ﬂora of Western Europe, USA,

Canada, Central America, Caribbean islands, Ama-

zon, French Polynesia, including, medicinal plants,

invasive plants, weeds.

tion, the login procedure is very important due its

related to the safety of student’s personal data. On

the other hand, login possibility is important to save

achievements, progress, and communications which

motivates student.

Only LeafSnap doesn’t use the additional account

et al (it automatically connected to Google account).

Almost all apps request their own account. Seek re-

quests Inaturalist account (to connect with social net-

work Inaturalist). Apps such as FloraIncognita starts

from account creation page; PictureThis starts from

payment page which may be a disadvantage for using

by pupils. Login process of Flora Incognita, Plant-

Net, PlantSnap, Seek, Picture-This, and PictureThis’s

aggressive advertising is presented in ﬁgure 1.

The detailed video instructions are sent to the e-

mail only using PlantSnap app (English voice and

Russian subtitles). Other apps provide instructions in

app. PlantNet does not have Instructions et al. In-

structions of PictureThis’s are very simple. LeafS-

nap’s help is not displayed at the ﬁrst start; it is lo-

cated in a speciﬁc tab. Instructions in Flora Incognita

(a), PlantSnap (b), PictureThis (c) LeafSnap (d) and

Seek (e, f) apps is presented in ﬁgure 2.

Data and photo input process. According to

botanical science, the algorithm for determining a

plant includes: establishing the life form of the plant

(tree, bush, grass); then studying the vegetative parts

of the plant (leaves, stem). In addition, generative or-

gans (ﬂower or fruit) analysis is useful to determine a

speciﬁc species name. Flora incognita and LeafSnap

are provide addition of different part of the plant’s pic-

tures. The mechanism of processing can differ. For

example, Flora incognita process photos of different

parts of the plant; PlantNet are provides photography

and then choosing of the plant part (analyzing only

one photo).

Geographic location is very important to identify

many species. Picea omorika and Picea abies are very

similar species, but Picea omorika only in Western

Siberia and Eastern Bosnia and Herzegovina. Seek,

Comparing Google Lens Recognition Accuracy with Other Plant Recognition Apps

(a) (b) (c)

(d) (e) (f) (g)

Figure 1: Login process of Flora Incognita (a), PlantNet (b), PlantSnap (c), Seek (d), Picture-This (e), and PictureThis’s

aggressive advertise (f, g).

Flora Incognita, LeafSnap, PlantNet requests geolo-

cation access during the ﬁrst start. If the algorithm

for determining the plant in the application includes

the deﬁnition of life form, photographing the vegeta-

tive and generative organs, as well as the geographical

location of the object, the algorithm has evaluated as

completely correct. If the application of the plant is

based on the analysis of one image in a single click,

the algorithm has evaluated as simple. The interface

of different apps photo and data input is presented in

ﬁgure 3.

In general, all apps are free, but PlantSnap lim-

its identiﬁcations by 25 plants per account per day.

The programs can request or a single photo of the

plant or photos of different parts of plants (PlantNet).

LeafSnap provides automatic detection of the part of

the plant presented in the photo. In general, all pro-

grams provide the possibility of both, making a real-

life photo or uploading of photo made before.

Identiﬁcation results. All apps (except PlantNet

and Seek) provides information on the determined

plant. All data on the plant is very structured in all

apps and displayed for example in style: “Genus: Fu-

cus”.

FloraIncognita, PlantNet, PlantSnap provide inter-

action with other sources. Both, general sources such

as Wikipedia and very speciﬁc sources such as Plants

for a Future are used to interact. The most interactive

is Plant net. It provides links to Catalogue of Life,

Plants for a Future and Wikipedia Flora Incognita,

AET 2020 - Symposium on Advances in Educational Technology

(a) (b) (c)

(d) (e) (f)

Figure 2: Instructions in Flora Incognita (a), PlantSnap (b), PictureThis (c) LeafSnap (d) and Seek (e, f) apps.

and in the case of Russian interface provides the link

with site www.plantarium.ru (ﬁgure 4). Comparison

results of mobile applications that can analyze plant

photos are presented in table 4.

There some very speciﬁc functions during identi-

ﬁcation:

• PictureThis can provide auto diagnose of plant’s

problem on pests and diseases (ﬁgure 5);

• PlantSnap ﬁnds the plant at amazon and provides

an infographic on solar activity, water usage and

activation temperature.

Comparing Google Lens Recognition Accuracy with Other Plant Recognition Apps

(a) (b) (c)

(d) (e) (f)

Figure 3: The interface of photo and data input of Flora Incognita (a), PlantNet (b) PlantSnap (c) PictureThis (d) LeafSnap

Seek (e) apps.

3.2 Infrastructure and Social

Environment

Some applications have their own approach to pro-

vide complex research of nature. Those features are

very useful to increase the motivation of students to

research nature. It’s worth noting that the most de-

veloped environment is in Seek used iNaturalist ap-

plication (developed by California Academy of Sci-

ence and National Geographic). Which delivers to

AET 2020 - Symposium on Advances in Educational Technology

(a) (b) (c) (d)

(e) (f) (g)

Figure 4: Data on identiﬁed plant Flora Incognita (a), PlantNet (b), PlantSnap (c, d), PictureThis (e), LeafSnap (f), and Seek

(g).

students and teachers’ powerful systems of different

instruments.

Photo sharing and communications. PlantNet

provides the feed of photos to identify, shared by

other users of PlanNet. The information in the feed

is divided into classes “identiﬁed”, “unidentiﬁed” and

“All”-ﬁlter (displays both, identiﬁed and unidenti-

ﬁed). The items in feed with an “identiﬁed” ﬁlter will

display already identiﬁed plants by users and “uniden-

tiﬁed” will display not-identiﬁed pictures updated by

users. The most perspective is using “unidentiﬁed”

feed which may be useful in a few cases:

• To help with identifying of the plant

• To train own identiﬁcation skills by providing

identiﬁcation of pictures of others

• To share thoughts in the ﬁeld of botanic, commu-

nicate with other researchers, and to provide so-

cial science networking.

Personal journals. The ﬁrst instrument to mo-

tivate is personal journals of observation and iden-

tiﬁcation. This is a very common feature. For ex-

ample, Flora Incognita has tab “My observations”;

PictureThis has “My garden”; Leaf snap has “My

plants”. However, some apps do not provide explic-

itly personal journal. For example, PlantNet saves just

the history of observations.

Projects and social. Seek provides collabora-

tion by providing projects. Users can ﬁnd and chose

projects they like and join be involved in them. It’s

worth note, that the app is very widespread and there

Comparing Google Lens Recognition Accuracy with Other Plant Recognition Apps

Table 4: Comparison results of mobile applications that can analyze plant photos.

App title Plants amount

in database

Correctness of the analyzing pro-

cess

Links with other information services

Flora

Incognita

4800 (only

German)

The analysis algorithm is correct Links to Catalogue of Life, Plants for a Fu-

ture and Wikipedia. Flora Incognita with

Russian interface provides links to the Rus-

sian site www.plantarium.ru

PlantNet 21920 The analysis algorithm is com-

pletely correct

Only the name of the plant. Includes ele-

ments of social networks (by sharing plants

student found and subscriptions). It con-

tains links to Wikipedia.

PlantSnap 585000 The analysis algorithm is simple. Has own description. Provides searching

on Amazon to buy it.

Picture

This

10000 The analysis algorithm is simple Provides very structured information (in-

cluding type, lifespan, height, ﬂower diam-

eter), care aspects, usage of the plant.

LeafSnap No data The analysis algorithm is correct.

Determining includes evaluation of

health state (healthy and unhealthy).

Contains links to Wikipedia, Pl@ntUse,

Global Biodiversity Information Facility.

Seek No data The analysis algorithm is the sim-

plest. The achieves are given for

users after some successful identiﬁ-

cations

Has no detailed description, but propose

“species nearby in this taxon”.

are even projects in Ukraine. The interfaces of project

selection and concrete project interface are presented

in ﬁgure 6a.

Achievements. The Seek-identiﬁcation app pro-

vides a signiﬁcantly different approach to increase

students’ motivation. It provides achieves for each

plant students found which motivates students to get

new and new researches from time to time. The ef-

fect of achievement affects the brain as exaltation and

people want it again and again. This is used in games

to motivate students to play again. In the case of Seek,

some factors will motivate students to research nature.

The iNaturalist propose observing of plant and an-

imal kinds student can ﬁnd nearby. This feature is

activated by the “Exploring All” function and choos-

ing “My location”. Also, based on location students

can use Missions which provides quests for students

to do, for example, to ﬁnd “Rock Pigeon”. So, stu-

dents can observe nature nearby in general to study

it and the program will stimulate students by com-

pleting the missions. The Exploring All and Missions

functions are presented in ﬁgure 6b,c.

3.3 Analysis of Application

Identiﬁcation Accuracy

PlantNet is the easiest app to install. Also, pretty easy

to install are Google Lens, LeafSnap and Flora Incog-

nita. Apps Google Lens, LeafSnap, Flora Incognita,

Seek to have the simplest interface. Google Lens,

PlantSnap, PictureThis, and PlantNet are character-

ized by the most uncomfortable process of identiﬁca-

tion which can be complicated for teachers. Results of

detailed analyses on plant identiﬁcation applications

are presented in ﬁgure 7.

In general, Google Lens, LeafSnap, Flora Incog-

nita, PlanNet, Seek has evaluated as most usable and

they were detailly researched. However, the total

number of points each of the applications received is

presented in ﬁgure 8.

The most accurate apps are Google Lens with

92.6% of correctness of the identiﬁcation. Flora

Incognita provides correct identiﬁcation of 71% of

cases; PlantNet – in 55%; Seek – in 76%. In our pre-

vious work, we demonstrated that Google Lens does

not differentiate native species from Ukraine. It seems

that Seek, PlantNet and Google Lens mostly use data

of American and European kinds of plants to training

the neural network and they have missed under identi-

ﬁcation of speciﬁc Ukrainian’s kinds of plants. Flora

Incognita was characterized by signiﬁcantly different

speciﬁc of analyses; it may be due to Flora Incognita

uses a Russian database (similar to the Ukrainian re-

gion). This may explain a higher percent of identiﬁca-

tion accuracy of Flora Incognita, compared to Plant-

Net. Results on analysis quality of apps which are

identiﬁed plants are presented in ﬁgure 9.

From the point of view of botanical science, the

AET 2020 - Symposium on Advances in Educational Technology

(a)

(b)

Figure 5: PictureThis’ plant’s auto diagnose on pests and diseases function: photo input interface (a) and the result of the

analysis (b).

possibility to add different parts the plants and choos-

ing of the plant’s type and geolocation access must af-

fect the identiﬁcation process correctness. However,

taking to account the results of the experiment, appli-

cations with a simple algorithm deﬁnition (analysis

of a single image) more accurately identify plants. It

seems that internal algorithms of identiﬁcation (due

to higher statistical characteristics of neural network)

and fullness of database is more important than cor-

rectness of data input or taking to account of geoloca-

tion.

So, Google Lens is characterized by the highest

quality of analysis which may be due to the better

recognition algorithm and the most trained neural net-

work. However, it still may be relevant to use other

applications in case it will be characterized by sig-

niﬁcantly higher parameters of use. To evaluate this,

a similar survey as used for other plant identiﬁcation

applications was used for Google Lens. Google Lens

has the most intuitive interface, is the most easily

loaded, and gives the most accurate deﬁnition result

and therefore is characterized by the highest general

evaluation with 4.6 points of interface analysis. This

is signiﬁcantly higher than marks for other apps.

Therefore, Google Lens is the most recommended

app to use. Talking to account, results of usability

analysis, and quality of analysis, for those students

and teachers who do not like Google Lens app, it is

Comparing Google Lens Recognition Accuracy with Other Plant Recognition Apps

(a) (b) (c)

Figure 6: The Exploring All (a), Missions functions (b) and concrete project (c) functions.

possible to use Seek or Flora Incognita, but Plant-

Net can’t be recommended to use due to low accuracy

which may provide up to half of incorrect analyzing

results.

3.4 Advantages of using Mobile Phone

Application in the Educational

Process

In our opinion, the use of mobile applications that

identify plants during the education process has the

following functions:

1. Creating a learning environment. Even in the

works of the classic of pedagogical thought

M. Montessori, it was proved that the environ-

ment should develop the child. Mobile applica-

tions to a greater or lesser extent create such an

environment. For example, Seek stimulates the

child to search for new plant objects, manages the

process of photographing plants, provides links to

additional information about the plant, creates its

own synopsis for the child, rewards the child with

“achievement”.

2. Cognitive function. Only 70 hours are allotted to

study all plants in Ukrainian schools. There is

very little time. Mobile applications allow stu-

dents to learn about the diversity of the plant

world.

3. Training function. Due to the limited number of

teaching hours, the teacher cannot focus enough

on the developed practical skills, such as deter-

mining the life form of plants (bush, grass, tree,

vine). Such skills are developed as a result of re-

peated training. Some applications, such as Flora

Incognita, request a deﬁnition of life form. And

this contributes to the formation of this skill.

The use of mobile applications promotes the de-

velopment of students with the following competen-

cies:

1. Competencies in the ﬁeld of natural sciences, en-

gineering, and technology (Gil-Quintana et al.,

2020). When using mobile applications, students

gain experience in the study of nature.

2. Environmental competence (Morkun et al., 2018).

Some applications, such as Seek, explain the rules

of behavior in nature.

3. Information and communication competence

(Kuzminska et al., 2019). The use of mobile ap-

plications allows students to demonstrate the safe

use of technology for learning.

4. Lifelong learning competence (van den Broeck

et al., 2020). The use of mobile applications

teaches students to ﬁnd opportunities for learning

and self-development throughout life.

AET 2020 - Symposium on Advances in Educational Technology

Figure 7: Results of detailed results on plants identiﬁcation applications usability analysis.

Figure 8: Integrated results on the usability of plants identiﬁcation applications.

Figure 9: Results on analysis quality of apps which is iden-

tiﬁed plants.

4 CONCLUSION

Apps related to plant identiﬁcations can be referred to

as those which can analyze photos, devoted to manual

identiﬁcation, and apps devoted to plant care moni-

toring. LeafSnap, Flora Incognita, PlanNet, Seek are

the most usable plant identiﬁers apps during STEM-

based classes.

It is shown that Google Lens characterized by the

highest mark of usability compare to PlantNet, Flora

Incognita, and Seek. In addition Google Lens has

the highest accuracy of identiﬁcation rate (92.6%).

Seek and Flora Incognita has signiﬁcantly lower accu-

racy of identiﬁcation rate 76% and 71%, respectively.

PlantNet provides correct identiﬁcation only in 55%

of case which is signiﬁcantly and can’t be used dur-

ing education at all. Therefore, Google Lens is the

most recommended app to use during biology classes.

Comparing Google Lens Recognition Accuracy with Other Plant Recognition Apps

However, for those students and teachers who do not

like the Google Lens app, it is possible to use Seek or

Flora Incognita.

However, Google Lens provides only identiﬁca-

tion without ecosystem. The Seek mobile application

can be used as a complex learning environment. It in-

cludes communications between naturalists, achieve-

ment system for motivation of the students and other

advantages.

In general, it is proven that using of AR-based

identiﬁcation programs characterized by positive ef-

fect on education process and provides development

of the competencies.

REFERENCES

Agustina, W. W., Sumarto, S., and Trisno, B. (2019). Aug-

mented reality based on stem for supporting science

literacy in vocational education. Journal of Physics:

Conference Series, 1375:012088.

Antonietti, A., Imperio, E., Rasi, C., and Sacco, M. (2001).

Virtual reality and hypermedia in learning to use a

turning lathe. Journal of Computer Assisted Learn-

ing, 17(2):142–155.

Chorna, O., Hamaniuk, V. A., and Uchitel, A. (2019). Use

of YouTube on lessons of practical course of German

language as the ﬁrst and second language at the ped-

agogical university. CEUR Workshop Proceedings,

2433:294–307.

Clark, A. C. and Ernst, J. V. (2008). STEM-Based Com-

putational Modeling for Technology Education. The

Journal of Technology Studies, 34(1):20–27.

de Jong, T. (2019). Moving towards engaged learning in

STEM domains; there is no simple answer, but clearly

a road ahead. Journal of Computer Assisted Learning,

35(2):153–167.

Devi, A. and Rav, G. (2018). Reviews on Augmented Real-

ity: Google Lens. International Journal of Computer

Trends and Technology, 58:94–97.

du Plessis, L. K. (2015). Through the Google Lens: Devel-

opment of lecturing practice in Photography. Master

of technology in photography, Durban University of

Technology. https://openscholar.dut.ac.za/bitstream/

10321/1437/1/DU%20PLESSIS 2015.pdf.

Dziabenko, O. and Budnyk, O. (2019). Go-Lab ecosystem:

Using online laboratories in a primary school. In ED-

ULEARN19 Proceedings, 11th International Confer-

ence on Education and New Learning Technologies,

pages 9276–9285. IATED.

Gil-Quintana, J., Malvasi, V., Castillo-Abdul, B., and

Romero-Rodr

ıguez, L. (2020). Learning leaders:

Teachers or youtubers? participatory culture and stem

competencies in italian secondary school students.

Sustainability (Switzerland), 12(18).

Hussein, M. and N

atterdal, C. (2015). The Beneﬁts of

Virtual Reality in Education: A Comparison Study.

Bachelor of science thesis in software engineering and

management, University of Gothenburg, Chalmers

University of Technology. https://gupea.ub.gu.se/

bitstream/2077/39977/1/gupea 2077 39977 1.pdf.

Joiner, I. A. (2018). Chapter 6 - virtual reality and aug-

mented reality: What is your reality? In Joiner, I. A.,

editor, Emerging Library Technologies, Chandos In-

formation Professional Series, pages 111–128. Chan-

dos Publishing.

Jong, T. D., Sotiriou, S., and Gillet, D. (2014). Innovations

in STEM education: the Go-Lab federation of online

labs. Smart Learning Environments, 1(3):1–16.

Kapici, H. O., Akcay, H., and de Jong, T. (2019). Us-

ing Hands-On and Virtual Laboratories Alone or To-

gether—Which Works Better for Acquiring Knowl-

edge and Skills? Journal of Science Education and

Technology, 28(3):231–250.

Khine, M. S., editor (2018). Computational Thinking in the

STEM Disciplines: Foundations and Research High-

lights. Springer, Cham.

Kinateder, M., Ronchi, E., Nilsson, D., Kobes, M., M

uller,

M., Pauli, P., and M

uhlberger, A. (2014). Virtual Re-

ality for Fire Evacuation Research. In Proceedings of

the 2014 Federated Conference on Computer Science

and Information Systems, volume 2, pages 313–321.

Kuzminska, O., Mazorchuk, M., Morze, N., Pavlenko, V.,

and Prokhorov, A. (2019). Study of digital compe-

tence of the students and teachers in ukraine. Com-

munications in Computer and Information Science,

1007:148–169.

Lee, E. A. L. and Wong, K. W. (2014). Learning with

desktop virtual reality: Low spatial ability learners are

more positively affected. Computers and Education,

79:49–58.

Marienko, M. V., Nosenko, Y. H., and Shyshkina, M. P.

(2020). Personalization of learning using adaptive

technologies and augmented reality. CEUR Workshop

Proceedings, 2731:341–356.

Mart

ın-Guti

errez, J., Fabiani, P., Benesova, W., Meneses,

M. D., and Mora, C. E. (2015). Augmented real-

ity to promote collaborative and autonomous learning

in higher education. Computers in Human Behavior,

51:752–761.

Modlo, Y. O., Semerikov, S. O., Nechypurenko, P. P., Bon-

darevskyi, S. L., Bondarevska, O. M., and Tolmachev,

S. T. (2019). The use of mobile Internet devices

in the formation of ICT component of bachelors in

electromechanics competency in modeling of techni-

cal objects. CEUR Workshop Proceedings, 2433:413–

428.

Morkun, V., Semerikov, S. O., Morkun, N. V.,

Hryshchenko, S., and Kiv, A. E. (2018). Deﬁning

the structure of environmental competence of future

mining engineers: ICT approach. CEUR Workshop

Proceedings, 2257:198–203.

Park, N. (2011). The Development of STEAM Career

Education Program using Virtual Reality Technology.

Journal of Physics A: Mathematical and Theoretical,

44(8):085201.

Potkonjak, V., Gardner, M., Callaghan, V., Mattila, P.,

Guetl, C., Petrovi

c, V. M., and Jovanovi

c, K. (2016).

AET 2020 - Symposium on Advances in Educational Technology

Virtual laboratories for education in science, technol-

ogy, and engineering: A review. Computers and Edu-

cation, 95:309–327.

Sahin, S. (2006). Computer simulations in science educa-

tion: Implications for distance education. Turkish On-

line Journal of Distance Education, 7(4):132–146.

Sala, N. (2014). Applications of Virtual Reality Technolo-

gies in Architecture and in Engineering. International

Journal of Space Technology Management and Inno-

vation, 3(2):78–88.

Sarabando, C., Cravino, J. P., and Soares, A. A. (2014).

Contribution of a Computer Simulation to Students’

Learning of the Physics Concepts of Weight and Mass.

Procedia Technology, 13:112–121.

Shapovalov, V. B., Atamas, A. I., Bilyk, Z. I., Shapo-

valov, Y. B., and Uchitel, A. D. (2018). Structuring

augmented reality information on the stemua.science.

CEUR Workshop Proceedings, 2257:75–86.

Shapovalov, V. B., Shapovalov, Y. B., Bilyk, Z. I., Ata-

mas, A. I., Tarasenko, R. A., and Tron, V. V. (2019).

Centralized information web-oriented educational en-

vironment of Ukraine. CEUR Workshop Proceedings,

2433:246–255.

Shapovalov, V. B., Shapovalov, Y. B., Bilyk, Z. I., Megalin-

ska, A. P., and Muzyka, I. O. (2020a). The Google

Lens analyzing quality: An analysis of the possibility

to use in the educational process. CEUR Workshop

Proceedings, 2547:117–129.

Shapovalov, Y. B., Shapovalov, V. B., Andruszkiewicz, F.,

and Volkova, N. P. (2020b). Analyzing of main trends

of STEM education in ukraine using stemua.science

statistics. CEUR Workshop Proceedings, 2643:448–

461.

Sifuna, J. (2016). Computer Modeling for Science, Tech-

nology, Engineering and Mathematics Curriculum in

Kenya: A Simulation-Based Approach to Science Ed-

ucation. Science Journal of Education, 4(1):1.

Stryzhak, O., Prychodniuk, V., and Podlipaiev, V.

(2019). Model of Transdisciplinary Representation of

GEOspatial Information. In Ilchenko, M., Uryvsky,

L., and Globa, L., editors, Advances in Informa-

tion and Communication Technologies, pages 34–75,

Cham. Springer International Publishing.

Syawaldi, F. A., H, M. Z., and Apandi, Y. (2019). Aug-

mented Reality (Studi Kasus : Google Lens). Infor-

man’s – Jurnal Ilmu-ilmu Informatika dan Manaje-

men, 2(1).

van den Broeck, L., de Keyzer, J., Kyndt, E., Daems, W.,

Valcke, M., and Langie, G. (2020). Learning has no

end - Lifelong learning competences for engineering

students. In SEFI 48th Annual Conference Engaging

Engineering Education, Proceedings, pages 104–111.

Zantua, L. S. O. (2017). Utilization of Virtual Real-

ity Content in Grade 6 Social Studies Using Af-

fordable Virtual Reality Technology. Asia Pa-

ciﬁc Journal of Multidisciplinary Research, 5(2):1–

10. http://www.apjmr.com/wp-content/uploads/2017/

05/APJMR-2017.5.2.2.01.pdf.

Comparing Google Lens Recognition Accuracy with Other Plant Recognition Apps