Viral diseases are main problems of poor yields for cassava, the second-largest provider of carbohydrates in Africa.
At least 80% of small-holder farmer households in Sub-Saharan Africa grow cassava. Since many of these farmers have smart phones, they can easily obtain photos of diseased and healthy cassava leaves on their farms, allowing them to use computer vision techniques to monitor the disease type and severity and increase yields.
The scanning results will be displayed in the 5 classes like
+ Cassava Bacterial Blight (CBB)
+ Cassava Brown Streak Disease (CBSD)
+ Cassava Green Mottle (CGM)
+ Cassava Mosaic Disease (CMD)
+ Healthy
Accuracy may be decreased in depending on sunlight or shade. As the camera continues to operate, please turn off the app when not in use. Thank you.
Lets watch the demo: https://youtu.be/iLaE9Jih1jE
This app enables the use of computer vision and deep learning technologies to scan the aforementioned disease types such as CBB, CBSD, CGM, CMD, and healthy in increasing yields. There is a huge image database (total of 21,397 images/5 classes: CBB, CBSD, CGM, CMD, and Healthy) in the tiny deep learning model. So, we also optimized the heavy deep learning model database (21,397 images/5 classes) for convenient use on mobile devices. In addition, It took few days to train the huge data by NVIDIA RTX 3090 x 2 machines.
Our intended purpose is to help the farmers build AI computer vision systems on their mobile devices.
We always welcome any questions like research report, paper and so on. Please contact us at [email protected]