Fast and accurate multitask saliency detection by considering the features of colour, texture, orientation and luminance

Detection of salient regions of an image is very essential in the fields of image processing applications such as image segmentation, image compression, and image retrieval. The major challenges in this area are clarity, speed of operation etc. Till now lot of methods have been evolved, but there is a need in the detection process to improve the clarity and speed. Multitask saliency detection aims at considering colour, texture, and orientation, as feature descriptors and ended with an appropriate result. Here in this proposed design the features of colour, texture, orientation and luminance are going to be considered to get an accurate and fast operation. Since luminance plays a vital role in an image, by including luminance the detection process will become more efficient. Also the overall process is fast, easy to implement and generates high quality saliency maps of the same size and resolution as the input image