Farming is the source of income for more than half of the Indian population. One of the serious issues in agriculture is the control of weeds growing among the plantation crops. At present weeds are being removed manually by farmers wherever possible, or weed killers/herbicides are being sprayed all over the field to keep them under control. This technique is very inefficient because chemicals are being sprayed on plantation crops also, which leads to, polluting the environment and health problems in humans. To avoid these consequences, a smart weed control system should be deployed. This paper focuses on detecting the weeds in the crop using convolutional neural network ,Image processing and IOT. CNN model is first trained by giving large images of weed and crop. This trained CNN model is deployed onto Raspberry pi. Images from camera is sent to raspberry pi based Machine learning system. Raspberry-pi performs Image segmentation, by dividing the image into small segments. The Segmentation Algorithm used is Watershed Segmentation Algorithm. Each segment is passed onto Trained CNN model for classifying as weed or crop. If it is weed, the area is marked in the original image as weed. In this manner all the weed segments are marked and the marked image can be sent to farmers through Email. The system was trained using 250 images of weed and crop and has given an Average Accuracy of 85% ,Average False ratio of 7%,Average False Acceptance ratio of 2.6%.

No abstract

Recognition of plant diseases early is one of the solution for preventing the losses in the yield and measure of agricultural product. The study of plant diseases signify the visually visible patterns seen on the plant. Health monitoring and disease detection on plant is very critical for sustainable agriculture. It is not easy to monitor the plant diseases manually. It needs lot of work, and expertise in the plant diseases, and in addition require the extreme processing time. Therefore, image processing is used for the identification of plant diseases. Disease detection involves the steps like image acquisition, image preprocessing, image segmentation, feature extraction and classification. Client Mobile application which capture image and send it to server and server executes the task and send back the result regarding the disease, symptoms and remedies on client mobile application. The technique used for the detection of plant diseases is to analyze plant leaves. It furthermore discusses about some segmentation and feature extraction algorithm used in the plant disease detection.