Image Partial Blur Detection and Classification

In this thesis, we propose a partially-blurred-image classification and analysis framework for automatically detecting images containing blurred regions and recognizing the blur types for those regions without performing blur kernel estimation and image deblurring. Our method attempts to tackle two major problems. One is blur detection with simultaneous extraction of blurred regions. The result in this step provides useful high-level regional information, facilitating a variety of region-based image applications, such as content-based image retrieval, object-based image compression, video object extraction, image enhancement, and image segmentation. It can also serve as one of the criteria of measuring the quality of the captured images. The second objective of our method is to automatically classify the detected blur regions into two types: near-isotropic blur (including out-of-focus blur) and directional motion blur. We classify image blur into these two classes because they are most commonly studied in the image restoration field. The classified blur images also easily find applications in motion analysis and image restoration. We develop several blur features modeled by image color, gradient, and spectrum information, and use feature parameter training to robustly classify blurred images. In our system, blur detection and blur type classification are achieved in two steps. First, blurred images with blurry regions are detected from the given images. In this step, we make use of a combination of three features, namely, Local Power Spectrum Slope, Gradient Histogram Span, and Maximum Saturation. Second, directional motion blurred regions are distinguished from out-of-focus blurred