Fourier Transform with Depth Quarter for Silent Object Detection

Object Detection identifies and isolates the most visible parts of a photograph. It is widely used in visual applications for object re-targeting, classification, image generation, tracking, picture retrieval, and more. The biggest obstacles for object identification algorithms include non-uniform illumination, postures, occlusion, and other variables that cause incorrect object detection. Traditional object-identification algorithms will perform poorly on complex backdrops. However, object identification systems using deep learning are in demand. Deep learning requires high-quality pictures for object identification training. Images in the datasets were taken under various lighting conditions. Low light causes data loss, making object identification harder. The thesis specifically enhances photographs to avoid the effects of poor illumination or damaged images, unlike existing detection methods, which directly recognize objects in degraded photos. This contradicts current detecting techniques. Picture augmentation is needed for many applications in many industries. Several approaches are used to improve images. These approaches reduce blur and noise to enhance a photo. Machine learning models' detection and classification skills are improved by these methods, as are object geometric features like edges. Published research describes histogram equalization, gamma correction, contrast limiting adaptive histogram equalization, and other image enhancing methods. Modern image processing uses complex algebra like the Fourier transform. A strategy for enhancing photographs is proposed in the thesis: Discrete Quaternion Fourier Transform (DQFT). The proposed approach can handle a larger dataset and achieve a 97% identification rate, outperforming CNN techniques. Compared to CNN, DFTCNN, RCNN, and Mask RCNN, our method can identify objects with accuracy of 0.8752, recall of 0.8268, and F1-score of 0.8295.