Plant identification? There’s an app for that—actually several!
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.
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 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 Plant & Pest Diagnostics and the MSU Herbarium, and help is available through the MSU 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 groups. Each year I evaluate a minimum of six apps that are available for both Android and iOS smartphones, with the best performers carrying over to the next year’s evaluation. I have evaluated 14 apps thus far (see complete list at the bottom of the article). Most of these apps use photo recognition software to identify plants from a photo, but some require 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 process I use for evaluating the apps is straightforward. I go out into my yard or neighborhood and use my phone to photograph approximately 12 plants, for which I already know the identity (2020 test images shown in Figures 1-12). Photos are not edited and aim 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 increase chances of success. Identification at all life stages is important for our students when making management decisions, so the photos I use get progressively more difficult to identify from my perspective.
I start with one or two flowering ornamentals (Figure 1), then I move on to flowering and vegetative broadleaf weeds (Figures 2-7), flowering and vegetative grass weeds (Figures 8-10), and finally in 2020 I included a couple weed seedlings (few true leaves, Figures 11-12). The same photos are inputted into each app. The results were assigned correct “+,” partial “+/-“ or incorrect “-“ in comparison to my personal identifications (Table 1). Correct “+” identifications are 100% accurate. Partial “+/-“ was assigned when the app correctly identified the plant to the genus level, but not down to the species [i.e., a photo of green foxtail was identified as Setaria faberi (giant foxtail) instead of the correct Seteria viridis] 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 100% correct. Ultimately, the apps are ranked each year based on the comparative number of correct identifications.
Most of the plant ID apps evaluated performed well for flowering ornamentals (at the species level, not specific cultivar) and flowering broadleaf weeds, such as periwinkle, Canada goldenrod and yellow woodsorrel (Figures 1-3). They have also improved in the identification of flowering grassy weeds over the last three years, with giant foxtail as an example (Figure 8). Vegetative grasses and seedlings remain difficult for most apps to successfully identify. Examples include tall fescue and seedlings of common lambsquarters, respectively (Figures 10 and 11). While I expect continued improvement for seedling broadleaves, grass identification by apps will likely remain problematic as the detailed features of grasses that allow one to distinguish them are often very small and difficult to photograph.
PictureThis has been the reigning champion of this test for three years in a row. In 2020, it successfully identified nine of the 12 plants correctly. Plants it did not identify correctly included perennial sowthistle (vegetative, Figure 6), tall fescue (vegetative, Figure 10) and a seedling of purslane speedwell (Figure 12). None of the six apps tested in 2020 correctly identified perennial sowthistle or the seedling purslane speedwell, and only LeafSnap fully identified tall fescue. 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 want to use the paid version need to pay attention and exit screens as needed.
iNaturalist was the runner up in 2020; the first year it was included in this test. In addition to incorrectly identifying tall fescue and seedling purslane speedwell, it received the “partial” rating for perennial sowthistle (Figure 6), black medic (Figure 7) and yellow nutsedge (Figure 9). iNaturalist has a few distinct advantages including the use of location data, the ability to input multiple photos and indicating the confidence level of its identifications. iNaturalist is free with no paid version and can be used to identify wildlife and insects (not tested here) as well as plants. However, its interface is not as user-friendly. There are two steps needed to enter the photos and then request the identification as opposed to the one-step approach (i.e., point-shoot-identify) of many of the other apps tested.
When using an app (or an internet search) to identify plants, 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, e.g. 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 down to the county level where herbarium specimens have been collected for each plant species. To confirm the identification of an ornamental plant, a botanic 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). Finally, numerous herbaria themselves have begun to digitize their collections into searchable databases with images, such as the Consortium of Midwest Herbaria and Integrated Digitized Biocollections.
All apps tested since 2018: FlowerChecker, Garden Answers, ID Weeds (Apple Store, GooglePlay), iNaturalist, LeafSnap, PictureThis, Plantifier (Apple Store, GooglePlay), PlantNet, PlantSnap, Seek by iNaturalist, Turf Doctor, Weed ID (Apple Store, GooglePlay) and Xarvio. Note that all were not tested each year.