Technical Support: AI Inspection of Agricultural Products

We will classify potatoes and detect tomato injuries using AI image inspection!

Recently, we have been receiving inquiries asking if the inspection of agricultural products we are currently conducting can be made a bit easier. Using vegetables provided by local farmers, we tested whether we could: ■ Classify potatoes by grade ■ Detect damage on tomatoes using SkyLogic. ▼ Potato Classification We photographed potatoes classified from A to C from different angles (a total of 66 images were taken), and after creating the training data and conducting inspections, we were able to classify them into grades A, B, and C. (All 30 images were classified correctly, achieving a 100 percent accuracy rate.) ▼ Detecting Damage on Tomatoes Since it was difficult to find damaged tomatoes, we tested whether we could detect damage on one type. Similar to the potatoes, we photographed them from different angles (12 images), created training data, and conducted inspections, resulting in the detection of damage as shown in the images. (All 30 images were inspected, and all damage was detected, achieving a 100 percent accuracy rate.)

basic information

Towards Smart Agriculture This time, we had a small sample size and conducted tests using only labeled images, resulting in very good outcomes. To accurately distinguish unknown images that are not labeled, it is necessary to train with more images. AI can learn to identify new defects as they arise, which means it has the characteristic of gradually learning and growing like a human. If you would like to try automatic identification of vegetables and fruits, please feel free to send us photos of grades and defects. Of course, real items are also acceptable! (Please be aware that our staff will enjoy them after testing.) Feel free to contact us.