Gray-level Image Segmentation Research Articles

Multiset neurons

The present work addresses the adoption of multiset similarity, more specifically the real-valued Jaccard and coincidence indices, as an element underlying artificial neurons. The overlap/interiority index, cosine similarity, and Euclidean distance are also considered. Special attention is given to the features adopted to characterize the patterns provided as input to neurons. After presenting the basic concepts related to real-valued multisets and the coincidence similarity index, including the generalization of the real-valued Jaccard and coincidence indices to higher orders, as well as a description of their special properties, we introduce multiset neurons with and without a non-linearity stage. Important issues related to the selectivity and sensitivity of the implemented comparisons, as well as the effect of localized perturbations of individual features are then addressed. We proceed to study the response of single linear multiset neurons respectively to the detection of gaussian two-dimensional stimulus in presence of displacement, magnification, intensity variation, noise and interference from additional patterns. It is shown that the real-valued Jaccard and coincidence approaches tend to be more robust and effective than the interiority index and the cross-correlation. The coincidence-based neurons are shown to have enhanced overall performance respectively to the considered type of data and perturbations. The potential of multiset neurons is further illustrated with respect to the challenging problem of color and gray-level image segmentation. The reported concepts, methods, and results have several implications not only for pattern recognition and machine learning, but also regarding several other related areas including signal processing, image analysis, and neuroscience.

Efficient image segmentation performance of gray-level image using normalized graph cut based neutrosophic membership function

The study of image segmentation is a crucial impression in image processing and computer vision appliances, which segments an input image into distinct non-overlapping homogenous divisions and helps to depict the image more conveniently. To improve the performance of the segmentation of gray-level images by introducing a normalized graph cut measure as a thresholding principle to separate an object from the background based on the neutrosophic membership function. We proposed an innovative neutrosophic approach combining a set of features of some efficient algorithms. The implementation of the proposed algorithm is known as the neutrosophic normalized graph cut (NNGC) method. In the gray image segmentation, the problem of wrongly segmentation and segmentation with low accuracy can identify by using this approach. This proposed algorithm is compared with the fuzzy entropy method, neutrosophic graph cut (NGC), classical graphcut, Otsu, and Kittler method. Moreover, we examine that in most cases, our algorithm gives the lowest absolute error, misclassification error, and higher values of signal to noise ratio values that improve the segmentation process of gray images. Finally, we analyze the change of different parameter values in the NNGC and the effect of the substitutes. Also, we discuss the computational complexity of neutrosophic weight matrix results with a weight matrix (classical) results.

Monocular vision and calculation of regular three-dimensional target pose based on Otsu and Haar-feature AdaBoost classifier

Using machine vision to identify and sort scattered regular targets is an urgent problem to be solved in automated production lines. This study proposed a three-dimensional (3D) recognition method combining monocular vision and machine learning algorithms. According to the color characteristics of the targets, to convert the original color picture into YCbCr mode and use the 2D Otsu algorithm to perform gray level image segmentation on the Cb channel. Then the Haar-feature training was carried out. The comparison of feature training and Haar method for Hough transform showed that the recognized time of Haar-feature AdaBoost trainer reached 31.00 ms, while its false recognized rate was 3.91%. The strong classifier was formed by weight combination, and the Hough contour transformation algorithm was set to correct the normal vector between plane coordinate and camera coordinate system. The monocular vision system ensured that the field of camera view had not obstructed while the dots were being struck. It was measured and calculated angles between targets and the horizontal plane which coordinate points of the identified plane feature. The testing results were compared with the Otsu and AdaBoost trainer where the prediction and training set have an error of no more than 0.25 mm. Its correct rate can reach 95%. It shows that the Otsu and Haar-feature based on AdaBoost algorithm is feasible within a certain error ranges and meet the engineering requirements for solving the poses of automated regular three-dimensional targets. Keywords: Otsu, Haar-feature, AdaBoost, 3D position, target pose, monocular vision, error analysis DOI: 10.25165/j.ijabe.20201305.5013 Citation: Li Y H, Wang H J, Zhou W L, Xue Z H. Monocular vision and calculation of regular three-dimensional target pose based on Otsu and Haar-feature AdaBoost classifier. Int J Agric & Biol Eng, 2020; 13(5): 171–180.

Monocular vision and calculation of regular three-dimensional target pose based on Otsu and Haar-feature AdaBoost classifier

Using machine vision to identify and sort scattered regular targets is an urgent problem to be solved in automated production lines. This study proposed a three-dimensional (3D) recognition method combining monocular vision and machine learning algorithms. According to the color characteristics of the targets, to convert the original color picture into YCbCr mode and use the 2D Otsu algorithm to perform gray level image segmentation on the Cb channel. Then the Haar-feature training was carried out. The comparison of feature training and Haar method for Hough transform showed that the recognized time of Haar-feature AdaBoost trainer reached 31.00 ms, while its false recognized rate was 3.91%. The strong classifier was formed by weight combination, and the Hough contour transformation algorithm was set to correct the normal vector between plane coordinate and camera coordinate system. The monocular vision system ensured that the field of camera view had not obstructed while the dots were being struck. It was measured and calculated angles between targets and the horizontal plane which coordinate points of the identified plane feature. The testing results were compared with the Otsu and AdaBoost trainer where the prediction and training set have an error of no more than 0.25 mm. Its correct rate can reach 95%. It shows that the Otsu and Haar-feature based on AdaBoost algorithm is feasible within a certain error ranges and meet the engineering requirements for solving the poses of automated regular three-dimensional targets. Keywords: Otsu, Haar-feature, AdaBoost, 3D position, target pose, monocular vision, error analysis DOI: 10.25165/j.ijabe.20201305.5013 Citation: Li Y H, Wang H J, Zhou W L, Xue Z H. Monocular vision and calculation of regular three-dimensional target pose based on Otsu and Haar-feature AdaBoost classifier. Int J Agric & Biol Eng, 2020; 13(5): 171–180.

Consistent validation of gray-level thresholding image segmentation algorithms based on machine learning classifiers

We propose a Machine Learning approach for Image Validation (MaLIV) to rank the performances of two or more outputs obtained from different gray-level thresholding image segmentation algorithms. MaLIV utilizes machine learning classifiers to rank automatically the outputs of different segmentation algorithms accounting for both the computational complexity of the validation experiment and for the robustness of its results. The proposed method resorts to subsampling to find Fisher consistent estimates of validity measures obtained from a sample of pixels of extremely-reduced size. To this purpose, subsampling is combined with three alternative approaches: learning curves, asymptotic regression and convergence in probability. Results of experiments involving the validation of five images segmented through thirteen different algorithms are presented.

An oscillatory network model with controllable synchronization and a neuromorphic dynamical method of information processing

A spatially two-dimensional oscillatory neural network model with inhomogeneous modifiable oscillatory coupling is designed and an adaptive dynamical method of brightness image segmentation (image reconstruction) based on self-organized cluster synchronization in the oscillatory network is developed. The method imitates the known phenomenon of dynamical binding via synchronization that is presumably used by a number of the brain neural structures in their work. The oscillatory-network approach demonstrates the following capabilities: (1) high-quality segmentation of real grey-level and color images; (2) selective image segmentation (exclusion of unnecessary information); (3) solution of the simplest problem of object selection in a visual scene—the problem of the successive selection of all spatially separated image fragments of almost equal brightness.

Noisy image segmentation based on nonlinear diffusion equation model

This paper addresses the segmentation problem in noisy image based on nonlinear diffusion equation model and proposes a new adaptive segmentation model based on gray-level image segmentation model. This model also can be extended to the vector value image segmentation. By virtue of the prior information of regions and boundary of image, a framework is established to construct different segmentation models using different probability density functions. A segmentation model exploiting Gauss probability density function is given in this paper. An efficient and unconditional stable algorithm based on locally one-dimensional (LOD) scheme is developed and it is used to segment the gray image and the vector values image. Comparing with existing classical models, the proposed approach gives the best performance.

Object selection in visual scene via oscillatory network with controllable coupling and self-organized performance

An oscillatory network model with controllable coupling and self-organized synchronization-based performance was developed for image processing. The model demonstrates the following capabilities: (a) brightness segmentation of real grey-level images; (b) colored image segmentation; (c) selective image segmentation--extraction of the subset of image fragments with brightness values contained in an arbitrary given interval. An additional capability--successive selection of spatially separated fragments of a visual scene--has been achieved via further model extension. The fragment selection (under minor natural restrictions on mutual fragment locations) is based on in-phase internal synchronization of oscillator ensembles, corresponding to all the fragments, and distinct phase shifts between different ensembles.

Noisy image segmentation based on wavelet transform and active contour model

This article addresses the noisy image segmentation problems based on wavelet transform and active contour model. In order to get better results, this article proposes a new segmentation and selective smoothing algorithm. First, a new adaptive segmentation model based on grey-level image segmentation model is proposed, and this model can also be extended to the vector value image segmentation. By virtue of the prior information of regions and boundary of image, a framework is established to construct different segmentation models using different probability density functions. A segmentation model exploiting Gaussian probability density function is given in this article. A penalizing term is employed to replace the time-consuming re-initialization process. An efficient and unconditional stable algorithm based on locally one-dimensional scheme is developed and it is used to segment the grey image and the vector value image. Second, in each stage of segmentation process, wavelet denoising algorithms are employed for different sub-regions independently, so that better segmentation and smoothing results can be obtained. Comparing with existing classical model, the proposed approach gives the best performance.

CMOS prototype vision chip with digital pixel structure for grey level image segmentation by means of thresholding and time multiplexing

In this article, a CMOS prototype vision chip with digital pixel structure for grey level image segmentation by means of thresholding and time multiplexing is presented. This approach splits scenes into m frames (one frame per grey level interval). One advantage about this design is that an analogue to digital converter is not required. Moreover, image acquisition and segmentation are performed at the same time by pixels that work simultaneously with each other. The performance from each pixel deals with a maximum quantum efficiency of 0.65, pixel size of 132 μm × 176 μm, fill factor of 0.78%, dark current of 15 mV/s, power dissipation per frame of 341 μW, minimum exposure time of 28.6 μs, maximum exposure time of 1.9 ms, random noise of 3 mV, optical dynamic range of 51 dB and majority of cells with 0–3% of mismatch. Scene decomposition into 256 images occurs in 30.5 ms with white illumination of 650 Lx.

CASE-BASED-REASONING FOR IMAGE SEGMENTATION

This paper proposes to use case-based-reasoning for grey-level image segmentation. Different approaches to image segmentation have been proposed in the literature. The selection of the segmentation approach and the assignment of the values to the parameters involved in the selected algorithm depend on image domain and on the specific application. Case-based-reasoning seems a promising way to make the above selection automatic. In this paper, we describe the results of a preliminary study done in this respect. In particular, we refer to the automatic selection of the values of the parameters for a new watershed image segmentation algorithm.

Image segmentation using a multilayer level-set approach

We propose an efficient multilayer segmentation method based on implicit curve evolution and on variational approach. The proposed formulation uses the minimal partition problem as formulated by D. Mumford and J. Shah, and can be seen as a more efficient extension of the segmentation models previously proposed in Chan and Vese (Scale-Space Theories in Computer Vision, Lecture Notes in Computer Science, Vol. 1682, pp. 141–151, 1999, IEEE Trans Image Process 10(2):266–277, 2001), and Vese and Chan (Int J Comput Vis 50(3):271–293, 2002). The set of unknown discontinuities is represented implicitly by several nested level lines of the same function, as inspired from prior work on island dynamics for epitaxial growth (Caflisch et al. in Appl Math Lett 12(4):13, 1999; Chen et al. in J Comput Phys 167:475, 2001). We present the Euler–Lagrange equations of the proposed minimizations together with theoretical results of energy decrease, existence of minimizers and approximations. We also discuss the choice of the curve regularization and conclude with several experimental results and comparisons for piecewise-constant segmentation of gray-level and color images.

Contrast enhancement and clustering segmentation of gray level images with quantitative information evaluation

Improper illumination and medium dispersing could occur in quite some gray level image collecting processes. Contrast enhancement and clustering segmentation are two effective approaches for the re...

Multiscale Bayesian texture segmentation using neural networks and Markov random fields

This paper presents a wavelet-based texture segmentation method using multilayer perceptron (MLP) networks and Markov random fields (MRF) in a multi-scale Bayesian framework. Inputs and outputs of MLP networks are constructed to estimate a posterior probability. The multi-scale features produced by multi-level wavelet decompositions of textured images are classified at each scale by maximum a posterior (MAP) classification and the posterior probabilities from MLP networks. An MRF model is used in order to model the prior distribution of each texture class, and a factor, which fuses the classification information through scales and acts as a guide for the labeling decision, is incorporated into the MAP classification of each scale. By fusing the multi-scale MAP classifications sequentially from coarse to fine scales, our proposed method gets the final and improved segmentation result at the finest scale. In this fusion process, the MRF model serves as the smoothness constraint and the Gibbs sampler acts as the MAP classifier. Our texture segmentation method was applied to segmentation of gray-level textured images. The proposed segmentation method shows better performance than texture segmentation using the hidden Markov trees (HMT) model and the HMTseg algorithm, which is a multi-scale Bayesian image segmentation algorithm.

Oversegmentation reduction in watershed-based grey-level image segmentation

Grey-level image segmentation is concerned with the identification of the objects of interest in a digital image. We suggest a segmentation technique based on the use of the watershed transformation to partition the image into homogeneous regions, and on the successive assignment of the regions to either the foreground or the background. Two alternative criteria to reduce the oversegmentation typically affecting the watershed transform are discussed. Region classification based on the grey-level changes of adjacent regions is presented, which works well for images where the boundary between foreground and background is perceived in correspondence with strong grey-level changes.

Texture and color segmentation based on the combined use of the structure tensor and the image components

In this paper, we propose a novel segmentation scheme for textured gray-level and color images based on the combined use of the local structure tensor and the original image components. The structure tensor is a well-established tool for image segmentation and has been successfully employed for unsupervised segmentation of textured gray-level and color images. The original image components can also provide very useful information. Therefore, a combined segmentation approach has been designed that combines both elements within a common energy minimization framework. Besides, an original method is proposed to dynamically adapt the relative weight of these two pieces of information. Quantitative experimental results on a large number of gray-level and color images show the improved performance of the proposed approach, in comparison to several related approaches in recent studies. Experiments have also been carried out on real world images in order to validate the proposed method.

Analogue CMOS prototype vision chip with fuzzy Kohonen network processing for grey level image segmentation

In this paper, the design and realization of an analogue CMOS prototype vision chip for grey level image segmentation for two regions is presented with Fuzzy-Kohonen Network processing as an alternative to neuromorphic and cellular neural networks approaches for vision chips. This alternative is due to the compensation that fuzziness gives in order to utilize simple analogue circuits with small layout areas instead of robust analogue circuits with bigger layout areas required. This helps to relieve the signal to noise ratio when crisp computations are present. The vision chip is based on the elaboration of an array of basic cells that work simultaneously. Every basic cell has embedded one vertical phototransistor and one network implemented under weak inversion techniques. The chip processes one image in 35 us with consumption of 733 uW per cell, signal to noise ratio of 43 dB and dynamic range of 49 dB.

Oscillatory network with self-organized dynamical connections for synchronization-based image segmentation

An oscillatory network of columnar architecture located in 3D spatial lattice was recently designed by the authors as oscillatory model of the brain visual cortex. Single network oscillator is a relaxational neural oscillator with internal dynamics tunable by visual image characteristics — local brightness and elementary bar orientation. It is able to demonstrate either activity state (stable undamped oscillations) or “silence” (quickly damped oscillations). Self-organized nonlocal dynamical connections of oscillators depend on oscillator activity levels and orientations of cortical receptive fields. Network performance consists in transfer into a state of clusterized synchronization. At current stage grey-level image segmentation tasks are carried out by 2D oscillatory network, obtained as a limit version of the source model. Due to supplemented network coupling strength control the 2D reduced network provides synchronization-based image segmentation. New results on segmentation of brightness and texture images presented in the paper demonstrate accurate network performance and informative visualization of segmentation results, inherent in the model.

A class of discrete multiresolution random fields and its application to image segmentation

In this paper, a class of Random Field model, defined on a multiresolution array is used in the segmentation of gray level and textured images. The novel feature of one form of the model is that it is able to segment images containing unknown numbers of regions, where there may be significant variation of properties within each region. The estimation algorithms used are stochastic, but because of the multiresolution representation, are fast computationally, requiring only a few iterations per pixel to converge to accurate results, with error rates of 1-2 percent across a range of image structures and textures. The addition of a simple boundary process gives accurate results even at low resolutions, and consequently at very low computational cost.

A cybernetic approach to the multiscale minimization of energy function: Grey level image segmentation

Segmentation is an important topic in computer vision and image processing. In this paper, we sketch a scheme for a multiscale segmentation algorithm and prove its validity on some real images. We propose an approach to the model based on MRF (Markov Random Field) as a systematic way for integrating constraints for robust image segmentation. To do that, robust features and their integration in the energy function, which directs the process, have been defined. In this approach, the image is first transformed to different scales to determine which one fits better to our purposes. Then, it is segmented into a set of disjoint regions, the adjacent graph (AG) is determined and a MRF model is defined on the corresponding AG. Robust features are incorporated to the energy function by means of clique functions and optimal segmentation is then achieved by finding a labeling configuration that minimizes the energy function using Simulated Annealing.