YOLO Based Deep Learning Model for Segmenting the Color Images

The first stage is to extract fine details from a picture using Red Green Blue (RGB) colour space image segmentation. Most grayscale and segmentation algorithms use original or updated fuzzy c-means (FCM) clustering. However, due two factors, the majority of these methods are inefficient fail produce acceptable results for photos. inclusion local spatial information often in high level computational complexity repetitive distance computation between clustering centres pixels within tiny adjacent window. second reason that typical neighbouring window tends mess up structure images. Color has been improved by introducing Deep Convolution Neural Networks (CNNs) object detection, classification semantic This study seeks build light-weight detector uses depth publically available dataset identify objects scene. It's likely output way expanding YOLO network's network architecture. Using Taylor based Cat Salp Swarm algorithm (TCSSA), weight suggested model modified improve accuracy region extraction findings. It possible test detector's efficacy comparing it various datasets. Testing showed capable segmenting input into multiple metrics bounding boxes. shows proposed achieved 0.20 Global Consistency Error (GCE) 1.85 Variation Information (VOI) on BSDS500 dataset, where existing techniques nearly 1.96 1.86 VOI 0.25 0.22 GCE same dataset.