No abstract

Coffee leaf disease recognition is important as its quality can be affected by the disease like -rust. This paper presents a coffee leaf disease recognition system with the help of gist feature. This research can help coffee producers in diagnosis of coffee plants in initial stage. Rocole coffee leaf dataset is considered in this study. Input image is preprocessed first. Resize and filtering is used as pre-processing work. Gist feature is extracted from pre-processed image. Extracted features are trained with machine learning algorithm. In testing phase, features are extracted and tested with trained ML model. Simulation is done with 10 fold cross validation. Different ML models are used and selected the best among them based on performance. SVM achieved overall 99.8% accuracy in recognizing coffee leaf disease.

Recognition of license plate is become an important research in computer vision. LPR is a part of surveillance system. Applications of LPR are like-traffic surveillance and monitoring, tracking of stolen car, maintaining parking lot and so on. This paper presents a new model to detect and recognize license plate of Bangladesh. The proposed model uses YCbCr color model for segmenting the input image. After taking an RGB image as an input, noises are removed through median filter. For suitable segmentation, the image is converted to YCbCr model. Based on the components of Y, Cb and Cr, the image is segmented. For Bangladeshi license plate, YCbCr model is fitted well for segmentation. A morphological opening operation is functioned on the segmented image. Using information of region properties, the image is filtered. Initially area and then aspect ratio parameters are used for filtering. Through this desired region is extracted. The proposed system does not require tilt correction. Using the proposed algorithm it is possible to extract characters easily from rotated plates also. Later characters are extracted separately followed by some morphological technique and region properties information. SVM classifier recognizes characters based on CNN features.

No abstract