27 September 2021 in Signal, Image and Video Processing
21 February 2023 in IETE Journal of Research
In countries like India, diseases in plants are a major concern in the agricultural sector. Crop loss due to diseases led to reduction in the quality and quantity of agricultural products. This also leads to economic losses. Hence, timely monitoring of plants is necessary. But monitoring diseases in large fields is a difficult task. To overcome this problem, effective management strategies should be taken to control diseases in plants. It can be done by acquiring data for disease identification and automation of the recognition of diseases. Deep learning is of great use in this area using the principles of object detection. In this paper, we are using YOLOv3 (you only look once) to determine the diseases in plants, based on the symptoms seen on the leaves. The advantage of using YOLOv3 is that multiple diseases can be detected on the image of a single leaf. An important feature of YOLOv3 is that it can detect small disease spots seen on the leaves. Here, we are concentrating on the bacterial spot disease seen on the bell pepper plant. The identification results show a mean average precision of 90%.
1 February 2021 in IOP Conference Series: Materials Science and Engineering
Our work provides a solution to people who are suffering from partial blindness due to diseases of the eye or due to accidents. Unlike people who are born blind, they depend a lot on other people for doing their day to day activities. Our project is a boon to such people as our end product; a smart walking stick detects the trained objects that are used daily by the person and intimates the person using audio messages. This project changes the visual world into an audio world by informing the visually impaired of the objects in their environment. These people can use this particular prototype for self -navigating their way. A YOLO (You look only once) algorithm is used in our project. Real-time objects in an image are detected with their names represented on a bounding box and these names are converted to speech signals. The conversion to audio signals is done by using an e-Speak tool which forms Googles Text to Speech (gTTS) system. The prototype consists of several modules. The Raspberry Pi camera module takes the image and transfers it to the Raspberry Pi desktop. Then, real-time object detection is carried out by using YOLO network. The detected image is converted to speech by using the gTTS module and the audio result is provided to the user through a headset. For achieving the required portability, the battery backup is being used.