Kindwise
| Industry | Machine learning |
|---|---|
| Founded | 2014 |
| Founder |
|
| Headquarters | , |
| Products | Plant.id, Plant.Health, Insect.id, Mushroom.id |
| Website | www |
FlowerChecker, also known as Kindwise,[1] is a company that uses machine learning to identify natural objects from images. This includes plants and their diseases, but also insects and mushrooms.[2][3][4] It is based in Brno, Czech Republic. It was founded in 2014 by Ondřej Veselý, Jiří Řihák, and Ondřej Vild, at the time Ph.D. students.[3][5]
Features & Tools
[edit]FlowerChecker offers multiple products.
The FlowerChecker app was launched in April 2014 for Android and later that year for iOS. [2][3][5] It enables users to submit photographs of the object they want to identify.[2][3]The photographs are then examined by an international team of experts in botany and horticulture.[2][3]
Plant.id is a machine learning-based plant identification API launched in 2018,[6] with the plant disease identification API, plant.health, released in April 2022.[4] The plant.id API is suitable for integration into other software, such as mobile apps[7] or urban trees from remote-sensing imagery.[8]
Other products include insect.id,[9] mushroom.id[10] and crop.health are machine learning-based identification APIs for the identification of insects, fungi and economically important plants,[11] respectively, and include also online public demos.
Recognition
[edit]In 2019, FlowerChecker won the Idea of the Year award in the AI Awards organized by the Confederation of Industry of the Czech Republic.[12] In 2020, an academic study comparing ten free automated image recognition apps showed that plant.id's performance excelled in most of the parameters studied.[7] In an independent study comparing different image-based species recognition models and their suitability for recognizing invasive alien species, the plant.id achieved the highest accuracy compared to other tools.[13] In a subsequent study, plant.id was utilized to evaluate urban forest biodiversity using remote-sensing imagery, achieving the highest accuracy in tree species identification among compared methods.[8]
Research activities
[edit]Flowerchecker cooperates with the Nature Conservation Agency of the Czech Republic on a biodiversity mapping project.[4]
FlowerChecker plans to adapt its services to participate in the control of invasive species. In 2022, the company entered a consortium to develop a weeder capable of in-row weed detection and removal.[14]
References
[edit]- ^ "Skenovat krajinu dronem, invazní druhy hubit robotem. Podivné vize ochrany přírody budoucnosti". Radio Wave (in Czech). 2023-11-28. Retrieved 2024-03-11.
- ^ a b c d "FlowerChecker aneb řekněte mi, co je to za kytku... Globální úspěch z Česka, který tvůrci nechtěli" [FlowerChecker: tell me what this plant is… Unwanted, yet global success coming from the Czech Republic]. tyinternety.cz (in Czech). 28 December 2014. Retrieved 14 November 2020.
- ^ a b c d e "Co je tohle za kytku? S určováním rostlin pomůže nová aplikace. Stačí poslat fotku" [What is the name of this plant? A new application will help with plant identification. Just send a photo]. Ekolist.cz (in Czech). 30 April 2014. Retrieved 14 November 2020.
- ^ a b c "Původně byznys nechtěli, ale nějak se to zvrhlo. Česká aplikace na rozpoznání kytek vydělala miliony" [Initially, they didn’t want a business, but somehow it went wrong. Czech plant identification application has made millions.]. cc.cz (in Czech). 4 May 2022. Retrieved 27 June 2022.
- ^ a b "Aplikace rozpoznává rostliny z celého světa. Díky botanikům i umělé inteligenci" [An application can identify plants from all over the world. Thanks to botanists and artificial intelligence]. Brněnský Deník (in Czech). 8 September 2016. Retrieved 14 November 2020.
- ^ "Tvůrci FlowerCheckeru spouštějí Shazam pro kytky. Plant.id staví na AI a má velké plány" [The creators of FlowerChecker are launching Shazam for plants. Plant.id is based on AI and has big plans]. tyinternety.cz (in Czech). 7 May 2018. Archived from the original on 12 May 2018. Retrieved 14 November 2020.
- ^ a b Jones, Hamlyn G (2020). "What plant is that? Tests of automated image recognition apps for plant identification on plants from the British flora". AoB Plants. 12 (6): plaa052. doi:10.1093/aobpla/plaa052. ISSN 2041-2851. PMC 7640754. PMID 33173573.
- ^ a b Velasquez-Camacho, Luisa; Merontausta, Esko; Etxegarai, Maddi; de-Miguel, Sergio (2024-04-01). "Assessing urban forest biodiversity through automatic taxonomic identification of street trees from citizen science applications and remote-sensing imagery". International Journal of Applied Earth Observation and Geoinformation. 128: 103735. doi:10.1016/j.jag.2024.103735. ISSN 1569-8432.
- ^ "insect.id AI Insect Identification API by kindwise". www.kindwise.com. Retrieved 2024-09-02.
- ^ "mushroom.id AI Mushroom Identification API by kindwise". www.kindwise.com. Retrieved 2024-09-02.
- ^ "crop.health AI Crop Disease Identification API by kindwise". www.kindwise.com. Retrieved 2024-09-02.
- ^ "V soutěži AI Awards uspěli tvůrci aplikací na určování rostlin nebo na rozpoznávání únosců po hlase" [Authors of applications for plant identification or voice recognition of abductors were successful at the AI Awards]. ihned.cz (in Czech). 13 May 2019. Retrieved 14 November 2020.
- ^ Jakuschona, Nick; Niers, Tom; Stenkamp, Jan; Bartoschek, Thomas; Schade, Sven (18 January 2022). "Evaluating image-based species recognition models suitable for citizen science application to support European invasive alien species policy". European Commission, Joint Research Centre. doi:10.2760/97305. ISBN 9789276467212. Retrieved 27 June 2022.
- ^ "Přijaté návrhy projektů do veřejné soutěže 6. veřejná soutěž programu TREND, PP1". Technologická agentura ČR (in Czech). Retrieved 2024-03-11.