Robust 2D Otsu’s Algorithm for Uneven Illumination Image Segmentation

Otsu’s algorithm is one of the most well-known methods for automatic image thresholding. 2D Otsu’s method is more robust compared to 1D Otsu’s method. However, it still has limitations on salt-and-pepper noise corrupted images and uneven illumination images. To alleviate these limitations and improve the overall performance, here we propose an improved 2D Otsu’s algorithm to increase the robustness to salt-and-pepper noise together with an adaptive energy based image partition technology for uneven illumination image segmentation. Based on the partition method, two schemes for automatic thresholding are adopted to find the best segmentation result. Experiments are conducted on both synthetic and real world uneven illumination images as well as real world regular illumination cell images. Original 2D Otsu’s method, MAOTSU_2D, and two latest 1D Otsu’s methods (Cao’s method and DVE) are included for comparisons. Both qualitative and quantitative evaluations are introduced to verify the effectiveness of the proposed method. Results show that the proposed method is more robust to salt-and-pepper noise and acquires better segmentation results on uneven illumination images in general without compromising its performance on regular illumination images. For a test group of seven real world uneven illumination images, the proposed method could lower the ME value by 15% and increase the DSC value by 10%.

Context-Aware Superpixel and Bilateral Entropy—Image Coherence Induces Less Entropy

Superpixel clustering is one of the most popular computer vision techniques that aggregates coherent pixels into perceptually meaningful groups, taking inspiration from Gestalt grouping rules. However, due to brain complexity, the underlying mechanisms of such perceptual rules are unclear. Thus, conventional superpixel methods do not completely follow them and merely generate a flat image partition rather than hierarchical ones like a human does. In addition, those methods need to initialize the total number of superpixels, which may not suit diverse images. In this paper, we first propose context-aware superpixel (CASP) that follows both Gestalt grouping rules and the top-down hierarchical principle. Thus, CASP enables to adapt the total number of superpixels to specific images automatically. Next, we propose bilateral entropy, with two aspects conditional intensity entropy and spatial occupation entropy, to evaluate the encoding efficiency of image coherence. Extensive experiments demonstrate CASP achieves better superpixel segmentation performance and less entropy than baseline methods. More than that, using Pearson’s correlation coefficient, a collection of data with a total of 120 samples demonstrates a strong correlation between local image coherence and superpixel segmentation performance. Our results inversely support the reliability of above-mentioned perceptual rules, and eventually, we suggest designing novel entropy criteria to test the encoding efficiency of more complex patterns.

Image retrieval of wool fabric. Part II: based on low-level color features

Color is difficult to distinguish by human vision and is described by keywords, resulting in low efficiency of wool fabric retrieval in factories at present. To obtain the process sheets of existing products and reduce the work of color measurement in sample analysis, this paper proposes an effective method based on dominant colors (DCs) and color moments (CMs) for wool fabric image retrieval. Firstly, the image was scaled to reduce computational time. Then, the hue, saturation, value color space was divided into 128 parts by the fast color quantization algorithm to extract the DCs of the image. Meanwhile, the CMs based on image partition were calculated in CIE L* a* b* color space to describe the spatial color information. Subsequently, different similarity measure methods were carried out based on the DC feature and CM feature. Finally, experiments were conducted on a wool fabric image database with 20,000 images for parameter optimization and verification. The average precision and recall were up to 87% and 44%, respectively. Experimental results show that the proposed scheme can retrieve images with the same or similar colors quickly and effectively and it outperformed other methods, providing referential assistance for the factory worker when retrieving wool fabrics.

Color–Texture Pattern Classification Using Global–Local Feature Extraction, an SVM Classifier, with Bagging Ensemble Post-Processing

Many applications in image analysis require the accurate classification of complex patterns including both color and texture, e.g., in content image retrieval, biometrics, and the inspection of fabrics, wood, steel, ceramics, and fruits, among others. A new method for pattern classification using both color and texture information is proposed in this paper. The proposed method includes the following steps: division of each image into global and local samples, texture and color feature extraction from samples using a Haralick statistics and binary quaternion-moment-preserving method, a classification stage using support vector machine, and a final stage of post-processing employing a bagging ensemble. One of the main contributions of this method is the image partition, allowing image representation into global and local features. This partition captures most of the information present in the image for colored texture classification allowing improved results. The proposed method was tested on four databases extensively used in color–texture classification: the Brodatz, VisTex, Outex, and KTH-TIPS2b databases, yielding correct classification rates of 97.63%, 97.13%, 90.78%, and 92.90%, respectively. The use of the post-processing stage improved those results to 99.88%, 100%, 98.97%, and 95.75%, respectively. We compared our results to the best previously published results on the same databases finding significant improvements in all cases.

Detecting Significant Changes in Image Sequences

In this chapter the authors propose an overview on contemporary artificial intelligence techniques designed for change detection in image and video sequences. A variety of image features have been analyzed for content presentation at a low level. In attempt towards high-level interpretation by a machine, a novel approach to image comparison has been proposed and described in detail. It utilizes techniques of salient point detection, video scene identification, spatial image segmentation, feature extraction and analysis. Metrics implemented for image partition matching enhance performance and quality of the results, which has been proved by several estimations. The review on estimation measures is also given along with references to publicly available test datasets. Conclusion is provided in relation to trends of future development in image and video processing.