Plant identification? There’s an app for that—actually several!

2022 update! Plant identification apps for smart phones have seen significant improvements over the past several years, offering the opportunity to take a photo and get an instant identification in many cases.

Students talk to each other while standing in a garden.
Figure 1. Students worked on the plant identification app evaluation at MSU’s W.J. Beal Botanical Garden.

We are driven to identify plants for many reasons; sometimes it is a curiosity about the world around us, other times it is out of the desire or need to manage areas like gardens, agricultural fields, restored habitats, and/or natural preserves. Plants are the foundation of food webs and they are tied to our understanding of how ecosystems function. Plant identification has been and continues to be a matter of familiarity, knowledge passed down through mentorship by family or friends, or perhaps something learned in school. One can also seek expert advice. Plant identification is one of the many services offered at Michigan State University (MSU) Plant & Pest Diagnostics and the MSU Herbarium, and help is available through the Michigan State University Extension Lawn and Garden Hotline (1-888-678-3464) and Ask Extension through eXtension.

There are now several smartphone apps available to assist with plant identification. As an expert in this area, it was with a bit of skepticism I began evaluating plant identification apps in 2018 for use in the Weed Science Laboratory class at MSU (i.e., CSS226L) and for presentations to various garden and commodity groups. Each year (2018-2020) I evaluated a minimum of six apps (available for both Android and iOS smartphones) using 10-12 plants, with the best performing apps carrying over to the next year’s evaluation. In the fall of 2021, I drastically increased the number of identifications used to rank the apps by involving 16 groups of university students enrolled in the lab.

Since 2018, the students and I have evaluated a total of 14 apps thus far (see complete list at the bottom of the article). In 2021, all the apps tested used photo recognition software to identify plants, but some tested in the past required more descriptive input from the user, similar to traditional plant keys. Most are free or have a free version. It is important to read all terms prior to downloading or purchasing apps. This assessment is for educational purposes only. Reference to commercial products or trade names does not imply endorsement by MSU Extension or bias against those not mentioned.

The students in the weed science lab learn plant identification skills as an integral part of the curriculum and the addition of the app evaluation supplements traditional methods. Lab groups were asked to photograph 10 plants labeled with their common and scientific names at the historic W.J. Beal Botanical Garden on the campus of MSU (Figure 1). Photos were not edited and aimed to realistically replicate the average person’s input. It should be noted that many of the apps provide detailed descriptions or videos on how to best take photos to increases chances of success. We did not discuss specific instructions prior to the class testing the apps, reflecting the average user’s likelihood of reading instructions.

Identifying weeds at all life stages is important for our students when making management decisions; therefore, they were required to photograph plant species across an array of growth habits and life stages. They were therefore required to photograph one plant from each of the following categories: flowering broadleaf ornamental species (Figure 2), flowering and vegetative broadleaf weeds (Figures 3 and 4), flowering and vegetative grass (or grass-like) weeds (Figures 5 and 6), and a seedling winter annual weed species (Figure 7). The last four plants were of their choosing, but it was recommended they use common agricultural and turf weeds from the garden’s collection.

Yellow cone flowers.
Figure 2. Three-lobed coneflower (Rudbeckia triloba) was an example of a flowering ornamental. Photo by Anna Baker, Abraham Fellabaum, Kelsey Klont and Michael Ozolins.
Common ragweed
Figure 3. Common ragweed (Ambrosia artemisiifolia) was an example of a flowering/fruiting broadleaf weed. Photo by Sara Verville, Keegan Humm, Darla Knuth and Kenny Kropf.
Birdsfoot trefoil
Figure 4. Birdsfoot trefoil (Lotus corniculatus ) was an example of a vegetative broadleaf weed/plant. Photo by Megan Carter, Carolina Freitas and Ray Rantz.
Yellow foxtail
Figure 5. Yellow foxtail (Setaria pumila) was an example of a flowering grass. Photo by Emma Woller, Larissa Lapak and Bredan Stuchell.
Bermuda grass
Figure 6. Bermuda grass (Cynodon dactylon) was an example of a vegetative grass. Photo by Matthew Fritz, Andrew Davis and Olivia Schassburger.
Henbit
Figure 7. Henbit (Lamium amplexicaule) was an example of a winter annual seedling. Photo by Erin Hill.

Each group was assigned six apps to evaluate from a list of eight (Table 1). Within groups, they input the same photos into each of the apps they were evaluating and recorded the apps’ identifications as correct, partial or incorrect in comparison to the specimen labels at the garden. Correct identifications were 100% accurate. Partial was assigned when an app correctly identified the plant to the genus level, but not to species [e.g., a photo of green foxtail was identified as Setaria faberi (giant foxtail) instead of the correct Setaria viridis (green foxtail)], or the correct answer was not the highest suggestion on the list for apps that make multiple suggestions. These answers may still be helpful towards a successful identification but are not entirely correct. Using this process, each of the eight apps was evaluated 90 to 140 times in 2021. Ultimately, the apps were ranked based on the comparative percentage of correct identifications.

Table 1. Plant identification apps evaluated and ranked by the MSU weed science laboratory students in fall 2021 (1= best performing).

App name

Placement

Garden Answers

8

iNaturalist*

5

LeafSnap

4

PlantNet*

2

PlantSnap

7

PlantStory*

3

PictureThis*

1

Seek

6

* Uses GPS location data, if allowed.

The top performing app in the 2021 evaluation outlined above was PictureThis, with 67% of the suggested identifications being correct (Figure 8). Following this lead, there was a cluster of three apps with about 50% accuracy: PlantNet, Plant Story and LeafSnap. These top four apps all displayed 50% or greater accuracy for flowering broadleaf ornamentals and broadleaf weeds. Surprisingly, the 2020-second runner-up, iNaturalist, came in fifth place with about 30% accuracy. Following is a more detailed review of these apps.

Graph
Figure 8. Overall performance of plant identification apps evaluated in fall 2021, in order of decreasing accuracy from top down.

PictureThis has been the reigning champion of this test for four years in a row. In 2021, it successfully identified the plants 67% of the 130 plants photographed at Beal Botanical Garden. Vegetative grass (or grass-like) weeds were the most challenging for this app to identify, with 43% accuracy. While PictureThis was less accurate at identifying grass-like weeds compared to other categories of plants, it should be noted that six of the other seven apps evaluated showed about 10% or less accuracy for this category. Grasses are difficult to identify using whole plant images, as close inspection of fine structures such as ligules or florets is often required for grass identification.

Of the 13 groups evaluating this app, 12 commented that it was their favorite because of both accuracy and ease of use. Users may appreciate the additional information provided with the identification in PictureThis, like frequently asked questions and environmental conditions for growth. PictureThis offers a free version of the app (tested here) and a paid version. The app is quite persistent in advertising the paid version. Those who do not wish to use the paid version need to pay attention and exit screens as needed.

PlantNet, Plant Story and LeafSnap performed similarly to each other. PlantNet’s strength was in identifying vegetative grass-like weeds (performing similarly to PictureThis) and seedling winter annuals (55% accuracy, 20% better performance than the other apps in this cluster). PlantStory was a newcomer to the evaluation this year and performed similarly to PictureThis (within 5%) regarding flowering ornamentals, as did LeafSnap. PlantStory also performed well with vegetative broadleaf weed identifications (78% accuracy, similar to PictureThis). Student reactions to these apps were mixed. Some remarked they were easy to use. A couple commented they disliked limited uses before paid version (PlantStory) and had difficulty uploading images (PlantNet).

iNaturalist was the runner up in 2020, but came in fifth in 2021 during the student assessment. Of the 11 groups evaluating this app, three commented that it was their first or second favorite and four said it was one of their least favorites. This divide could be an indicator of how well they read the directions. Positive attributes of iNaturalist include indicating the confidence level of its identifications and lack of paid version and advertisements (also true for its descendant app Seek). Several groups commented the app was not intuitive. For example, it was not immediately clear how to upload photos to get identifications (two-step process) compared to the point-shoot-identify model that most of the other apps use. With iNaturalist, it appears to be more critical to read the instructions and get to know the app before you use it. There is also a community feedback aspect to this app we have not yet explored.

When using apps or internet searches to identify plants, it is always advised to check the identification with a reputable source, such as government or university-affiliated sites. Searching by the scientific name (i.e., Latin genus and species, such as Amaranthus retroflexus) will yield the most accurate results as common names can differ by region, environment, etc. (e.g., redroot pigweed versus rough amaranth).

Some apps use location information when making the suggested identifications and some do not, therefore a suggested plant may not actually grow in the area where you took the photo. The USDA PLANTS Database is a good place to double check the known distribution of your identified plant. Michigan Flora is another good place to look; this shows county level distributions where herbarium specimens have been collected for each plant species since the 1800s. Numerous herbaria have begun to digitize their collections into searchable databases with images, such as the Consortium of Midwest Herbaria and Integrated Digitized Biocollections. To confirm the identification of an ornamental plant, a botanical garden resource such as Missouri Botanical Garden’s Plant Finder might be more appropriate (note this garden is in USDA Hardiness Zone 6b, Michigan ranges from 4a to 6b).

All apps tested since 2018: FlowerChecker, Garden Answers, ID Weeds (Apple Store, GooglePlay), iNaturalist, LeafSnap, PictureThis, Plantifier (Apple Store, GooglePlay), PlantNet, PlantSnap, PlantStory, Seek by iNaturalist, Turf Doctor, Weed ID (Apple Store, GooglePlay), Xarvio. Note that all were not tested each year.

Thank you to Matt Chansler, Angie Tenney and Alan Prather for reviewing this article.

Did you find this article useful?