Problem Statement –
One of the important sectors of Indian Economy is Agriculture. Employment to almost 50% of the countries workforce is provided by Indian agriculture sector. India is known to be the world’s largest producer of pulses, rice, wheat, spices and spice products. Farmer’s economic growth depends on the quality of the products that they produce, which relies on the plant’s growth and the yield they get. Therefore, in field of agriculture, detection of disease in plants plays an instrumental role. Plants are highly prone to diseases that affect the growth of the plant which in turn affects the ecology of the farmer. In order to detect a plant disease at very initial stage, use of automatic disease detection technique is advantageous. The symptoms of plant diseases are conspicuous in different parts of a plant such as leaves, etc. Manual detection of plant disease using leaf images is a tedious job. Hence, it is required to develop computational methods which will make the process of disease detection and classification using leaf images automatic.
Our solution –
Despite of the challenges given in the problem statement plant disease detection is still an active area of research. Numerous approaches have been proposed over the years. In our project we have created an AI based software which does detection, as mentioned above. Firstly a machine learning model is trained with images of many healthy and unhealthy leaves. And when a random leaf picture is shown to the software it immediately recognizes if the leaf is healthy or unhealthy. This enables the whole process of finding unhealthy leaves in the farm manually way faster as drones will click pictures of the leaves and these pictures will be fed to the software.
Project Tools and Methodology –
The project is built using Pictoblox AI Coding application. We have used Google teachable machine to build the Machine Learning Model to recognize healthy and unhealthy leaves. The model has been trained with two classes – good leaf and bad leaf. This model is then uploaded to pictoblox from google teachable machine and then the code logic is built in pictoblox.
We have used text to speech extension to convert texts to speeches said in the tenor voice.
We have also used the weather extension to show to current temperature humidity percentage and wind speed.
Time consumption and manual labor is reduced. Using our software a work which could easily take months can be done in few hour’s time which will be used to check the areas where the leaves are unhealthy and remove them.
Improvement Areas –
We can use more images to train the machine learning model and increase the model accuracy. The confidence score can be improved & used to determine state of the leaves more accurately.
Challenges Faced during the project –
Due to Machine Learning Model and lot of sprites lot of time the code was facing network bandwidth issue. Virtual Coordination during recording was also a bit challenging as screen share lower the bandwidth and reduce the video quality. The submission process is also difficult but our teacher helped us a lot. Thanks to Sarbani ma’am.