Agricultural mowers kill or kill thousands of animals each year due to the increased working widths and speeds of agricultural machinery. The detection and recognition of wild animals in the agricultural fields is important to reduce the mortality of wild animals and thereby promote species-appropriate agriculture. However, these data were not evaluated to assess the disease stages of the plant. The aim of the project is to develop, implement and evaluate an imaging software-based solution for the automatic detection and classification of plant leafdiseases, whichcontributes tothe automated detectionand classification ofanimals in thermograph. We present a fast, automatic, cost effective and accurate image processing solution. This solution consists of four main phases. First, the digital images are captured from the field or environment with digital cameras. Image preprocessing technology the noise is removed by filter technology. This paper is designed to help detect and classify leaf diseases using the multiclass SVM classification method. First, the affected region is discovered using segmentation through K-Means clustering, and then features (color and texture) are extracted. We then develop a cross-frame temporal patch verification method to determine if these region proposals are true animals or background patches. We construct an efficient feature description for animal detection using joint deep learning and histogram of oriented gradient features encoded with Fisher vectors. The Discrete Cosine Transform(DCT) is used to parameterize the thermal signature and thereby calculate a feature vectorthat will be used for subsequent classification. The proposed system detects and classifies diseases and animals with an accuracy of 95%.

.