Fuzzy-based segmentation of color natural images

This paper proposes unsupervised perceptual segmentation of natural color images using a fuzzy-based hierarchical algorithm. L*a*b* color space is used to represent color features and statistical geometrical features are adopted as texture features. A fuzzy-based homogeneity measure makes a fusion of color features and texture features. Proposed hierarchical segmentation method is performed in four stages: simple splitting, local merging, global merging and boundary refinement. Experiments on segmentation of natural color images are presented to verify the effectiveness of the proposed method in obtaining perceptual segmentation.

Image segmentation is the process of subdividing a digital image into its constitute regions such that pixels belong to the same region will be same based on some image property (such as grayscale value, color, texture) and pixels in the different group will be different based on the same image property. Till date, different researchers have taken image segmentation problem from a different point of view and developed several image segmentation algorithms. This paper is going to address an optimization-based approach in color image segmentation where optimized threshold value is chosen by maximizing the Kapur’s Entropy Function.

In this work four different machine learning approaches have been implemented to perform the color space transformation between CMYK and CIELAB color spaces. We have explored the performance of Support-Vector Regression (SVR), Artificial Neural Networks (ANN), Deep Neural Networks (DNN), and Radial Basis Function (RBF) models to achieve this color space transformation, both AToB and BToA direction. The data set used for this work was FOGRA53 which is composed of 1617 color samples represented both in CMYK and CIELAB color space values. The accuracy of the transformation models was measured in terms of ΔE* color difference. Moreover, the proposed models were compared, in practical terms, with the performance of the standard ICC profile for this color space transformation. The results showed that, for the forward transformation (CMYK to CIELAB), the highest accuracy was obtained using RBF. While, for the backward transformation (CIELAB to CMYK), the highest accuracy was obtained with DNN.

This paper presents a color recognition and segmentation of color image through a combination of a multi-scale fuzzy system, an image edge based on Prewitt operator and morphological operators. In the proposed algorithm, after converting image from RGB color space to hue-saturation-value (HSV) color space, different scales of fuzzy sets in hue channel is constructed according to the people's psychological cognition to color. The image color would be quickly recognized fuzzily as less than ten kinds on scale one. To improve the performance of the color recognition rate, recognized image need to be identified on scale two to distinguish different colors observed by human eyes with the same color scheme. Then, adopting Prewitt operator to extract image edge information and applying a sequence of some morphological operators to the edge image, completing the multi-scale segmentation of image with the integration of color and edge information. Finally, indicating its area and species of specific color. The proposed algorithm can automatically adjusted in the process of color recognition and segmentation of image, it achieves recognition and segmentation without supervision. The obtained result has a good consistency with man's subjective visual perception.

The topic of colour image segmentation has been and still is a hot issue in areas such as computer vision and image processing because of its wide range of practical applications. The urge has led to the development of numerous colour image segmentation algorithms to extract salient objects from colour images. However, because of the diverse imaging conditions in varying application domains, accuracy and robustness of several state-of-the-art colour image segmentation algorithms still leave room for further improvement. This dissertation reports on the development of a new image segmentation algorithm based on perceptual colour difference saliency along with binary morphological operations. The algorithm consists of four essential processing stages which are colour image transformation, luminance image enhancement, salient pixel computation and image artefact filtering. The input RGB colour image is first transformed into the CIE L*a*b colour image to achieve perceptual saliency and obtain the best possible calibration of the transformation model. The luminance channel of the transformed colour image is then enhanced using an adaptive gamma correction function to alleviate the adverse effects of illumination variation, low contrast and improve the image quality significantly. The salient objects in the input colour image are then determined by calculating saliency at each pixel in order to preserve spatial information. The computed saliency map is then filtered using the morphological operations to eliminate undesired factors that are likely present in the colour image. A series of experiments was performed to evaluate the effectiveness of the new perceptual colour difference saliency algorithm for colour image segmentation. This was accomplished by testing the algorithm on a large set of a hundred and ninety images acquired from four distinct publicly available benchmarks corporal. The accuracy of the developed colour image segmentation algorithm was quantified using four widely used statistical evaluation metrics in terms of precision, F-measure, error and Dice. Promising results were obtained despite the fact that the experimental images were selected from four different corporal and in varying imaging conditions. The results have indeed demonstrated that the performance of the newly developed colour image segmentation algorithm is consistent with an improved performance compared to a number of other saliency and non- saliency state-of-the-art image segmentation algorithms.

This paper describes an efficient algorithm for color image segmentation based on a multiresolution application of a wavelet transform and watershed segmentation algorithm. The procedure toward complete segmentation consists of four steps: pyramid representation, image segmentation, region projection and region merging. First, pyramid representation creates multiresolution images using a wavelet transform. Second, image segmentation segments the lowest-resolution image of the pyramid using a watershed segmentation algorithm. Third, the segmented low-resolution image with label is projected into a full-resolution image (original image) by inverse wavelet transform. Finally, region merging merges the segmented regions using fuzzy similarity. Experimental results of the presented method can be applied to the segmentation of noise or degraded images as well as reduce over-segmentation.

Image segmentation is a challenging task that has several applications in domains like medical imaging and surveillance. Among the various approaches proposed for this task, unsupervised methods have the advantage of being able to segment images without any assistance from the user. However, such methods often suffer from long runtimes and tend to be sensitive to the choice of parameters. Because of these problems, users will often prefer semi-supervised methods, which provide a more controllable output in the same amount of time. This paper proposes a new unsupervised approach, based on random walks, which maps each pixel to the most probable label in a local neighborhood. To make this approach more robust to the choice and learning of the parameters, we propose an efficient computational technique, in which the parameters and the segmentation probabilities are recomputed alternatively. We also describe a refinement strategy that improves the speed and accuracy of the segmentation by applying random walks at different scales. We evaluate the usefulness of our approach on the segmentation of natural images from the Berkeley segmentation database (BSD300). Results show our approach to have an accuracy comparable to state-of-the-art segmentation methods, while being much faster than these methods.

The most important properties of color spaces are without cross contamination between lightness, saturation and hue and with maximum perceptual uniformity after analyzing the deficiency of existing perception-based image processing problems. Unlike the traditional perception-based color spaces, this paper using multi-grid optimization and standard color-difference formulas defined a color lookup tables, constructs a new hue linear color space transformed images from an initial color space to the new color space. In order to verify the validity for image processing of the new space, we compared the color gamut mapping and image segmentation algorithms on the testing images with different color spaces. After comparing with the exiting color spaces, the experiment results showed color attributes of the new space free of cross contamination and with maximum perceptual uniformity which can improve the perception-based image processing algorithms accuracy.

In this paper, we present two new algorithms for cell image segmentation. First, we demonstrate that pixel classification-based color image segmentation in color space is equivalent to performing segmentation on grayscale image through thresholding. Based on this result, we develop a supervised learning-based two-step procedure for color cell image segmentation, where color image is first mapped to grayscale via a transform learned through supervised learning, thresholding is then performed on the grayscale image to segment objects out of background. Experimental results show that the supervised learning-based two-step procedure achieved a boundary disagreement (mean absolute distance) of 0.85 while the disagreement produced by the pixel classification-based color image segmentation method is 3.59. Second, we develop a new marker detection algorithm for watershed-based separation of overlapping or touching cells. The merit of the new algorithm is that it employs both photometric and shape information and combines the two naturally in the framework of pattern classification to provide more reliable markers. Extensive experiments show that the new marker detection algorithm achieved 0.4% and 0.2% over-segmentation and under-segmentation, respectively, while reconstruction-based method produced 4.4% and 1.1% over-segmentation and under-segmentation, respectively.

Machine vision has been widely applied in facility agriculture, and played an important role in obtaining environment information. In this paper, it is studied that application of image processing to recognize and locate corn tassel for corn detasseling machine. The corn tassel identification and location method was studied based on image processing and automated technology guidance information was provided for the actual production of corn emasculation operation. The system is the application of image processing to recognize and locate corn tassel for corn detasseling machine. According to the color characteristic of corn tassel, image processing techniques was applied to identify corn tassel of the images under HSI color space and Image segmentation was applied to extract the part of corn tassel, the feature of corn tassel was analyzed and extracted. Firstly, a series of preprocessing procedures were done. Then, an image segmentation algorithm based on HSI color space was develop to extract corn tassel from background and region growing method was proposed to recognize the corn tassel. The results show that this method could be effective for extracting corn tassel parts from the collected picture and can be used for corn tassel location information; this result could provide theoretical basis guidance for corn intelligent detasseling machine.

Pre-processing part in fingerprint image recognition system is fingerprint image segmentation. Even after the years of research in the field of image segmentation, it is still a challenging task. An image segmentation algorithm is proposed, named as Adaptive (scale) and Orientation (vector) algorithm, for effective segmentation of fingerprint images. The basic idea of the proposed algorithm is originated from the total variation models, along with two features of fingerprints, namely, scale and vector. It decomposes a fingerprint image into two layers: noisy and texture. Proposed segmentation algorithm is experimented and analyzed for two different fingerprint images. PSNR is the measuring parameter for checking the efficiency of algorithm. This algorithm is compared with adaptive and directional algorithm individually and concludes its better efficiency.

Color texture segmentation based on image pixel classification

Improving plant discrimination in image processing by use of different colour space transformations

This paper proposes a color image segmentation algorithm based on affinity propagation clustering. Firstly, the color image is converted to other color space; and then color image is sampled, and the sampling data is clustered by affinity propagation algorithm with given the number, then we can get their class label of the rest data according to the maximum similarity rules; finally, using the regional combined methods ,we can remove independent small regions, and get revised image segmentation result. The simulation experiment shows that this method can achieve the application of affinity propagation algorithm in large-scale color image segmentation. And it has a faster processing speed and satisfactory segmentation results, more in line with the human whole visual perception.

This paper presents an algorithm for image segmentation in HSI color space with application in cheese quality evaluation. The proposed algorithm uses two approaches to calculate segmentation thresholds for intensity, saturation and hue components- using medians and using average values. For experiments, there are used nineteen trademarks Bulgarian white cheese in brine that are produced of cow milk. The samples of cheese are evaluated by experts according to standard BDS 15612-83 for sensory evaluation of milk and dairy products. It is developed a special Likert scale to support expert's evaluation of broken surface of cheese (structure of this surface gives significant information about process of cheese production). All examined samples of cheese are captured with digital camera and with the proposed segmentation algorithm are processed their images. The ratio of white pixels to all, light gray, dark gray and black pixels to all are used for correlation analysis in comparison with score for broken surface which is given by experts using proposed Likert scale. The ratio of light gray pixels and white pixels to all pixels give the highest correlation coefficient with experts' evaluation and they could be used for objective evaluation of broken surface of white brined cheese.