Method for detecting judgment type visual saliency based on gradient direction histogram

Abstract

The invention relates to a method for detecting judgment type visual saliency based on a gradient direction histogram. The convention method has low resolution ratio, incomplete extracted object outline and high computation complexity. The method comprises the following steps of: firstly, extracting a color component diagram of an original image in a CIELAB space by a color transformation method; secondly, counting a local gradient direction histogram of every pixel point in the component diagram by using a sampling point in a central-peripheral computation structure; thirdly, calculating a local saliency judgment vector and a global saliency judgment vector of every pixel point; and finally, obtaining a final saliency judgment result by a linear weighting method. The method of the invention has a stronger response in a visually salient area and has higher inhibiting capacity in other non-salient areas.

Description

technical field

[0001] The invention belongs to the field of computer vision, and in particular relates to a judgment-type central-peripheral visual saliency detection method based on a gradient direction histogram. Background technique

[0002] Visual saliency plays an important role in the visual selective attention mechanism. Inspired by the biological visual system, the visual saliency computational model provides a fast and effective method for reducing the computational complexity of computer vision processing, and has been widely used in machine Vision, image processing, intelligent robots and other fields.

[0003] Currently, most visual saliency models are based on spatial (bottom-up) or object-based (top-down) processes. The former is based on feature integration theory and central-peripheral hypothesis, and its representative work is the computational model proposed by L.Itti et al. In their model, the input image is decomposed into multiple independent feature ...

Images