Image Thresholding Research Papers - Academia.edu (original) (raw)

Texture classification is a process to category a texture image into its related class. Texture features can be extracted by different methods, using structural, statistical, model-based and transform information. In this work geometric... more

Texture classification is a process to category a texture image into its related class. Texture features can be extracted by different methods, using structural, statistical, model-based and transform information. In this work geometric invariant moments (GM) feature is utilized as a rotation, scale and translation invariant classifier. For omitting the image intensity of the features, thresholding technique is used before feature extraction. After that a new optimized neural classifier employed to classify the input images into their category. The classifier consists of optimizing the weights of neural network by a new algorithm, Firefly algorithm. Brodatz database are used to perform the experiment and final results show 90.18% classification rate as the system efficiency.

In this study, a new classification algorithm based on multilevel thresholding for color images has been proposed. Initially, thresholds for each channel of color images are determined by using histograms and bee algorithm. Then, the... more

In this study, a new classification algorithm based on multilevel thresholding for color images has been proposed.
Initially, thresholds for each channel of color images are determined by using histograms and bee algorithm. Then,
the threshold values obtained are used for partition of RGB color space. Thus, pixels located in the relevant sub
cubes were assigned in the same cluster and subsequently the results have been obtained.

Selecting an optimal threshold value is the most important step in image thresholding algorithms. For a bimodal histogram which can be modeled as a mixture of two Gaussian density functions, estimating these densities in practice is not... more

Selecting an optimal threshold value is the most important step in image thresholding algorithms. For a bimodal histogram which can be modeled as a mixture of two Gaussian density functions, estimating these densities in practice is not simply feasible. The objective of this paper is to use adaptive particle swarm optimization (APSO) for the suboptimal estimation of the means and variances of these two Gaussian density functions; then, the computation of the optimal threshold value is straightforward. The comparisons of experimental results in a wide range of complex bimodal images show that this proposed thresholding algorithm presents higher correct detection rate of object and background in comparison to the other methods including Otsu’s method and estimating the parameters of Gaussian density functions using genetic algorithm (GA). Meanwhile, the proposed thresholding method needs lower execution time than the PSO-based method, while it shows a little higher correct detection rate of object and background, with lower false acceptance rate and false rejection rate.

This paper presents a fuzzy partition and Tsallis entropy based thresholding approach for multi-level image segmentation. Image segmentation is considered as one of the most critical tasks in image processing and pattern recognition area.... more

This paper presents a fuzzy partition and Tsallis entropy based thresholding approach for multi-level image segmentation. Image segmentation is considered as one of the most critical tasks in image processing and pattern recognition area. However, discriminating many objects present in an image automatically is the most challenging one. As a result, multilevel thresholding based methods gain importance in recent times, because of its ability to split the image into more than one segments. Efficiency of these algorithms still remains a matter of concern. Over the years, fuzzy partition of 1-D histogram has been employed successfully in bi-level image segmentation to improve the separation between object and the background. Here a fuzzy based technique is adopted in multi-level image segmentation scenario using Tsallis entropy based thresholding. Differential Evolution, a widely used meta-heuristic in recent times, is used for lesser computation time of the proposed algorithm. Both visual and statistical comparison of outcomes between Tsallis and Fuzzy - Tsallis entropy based methods are given in this paper to establish the superiority of the technique.

The paper focuses on the algorithms of the event detection in content-based video retrieval. Video has a complex structure and can express the same idea in different ways. This makes the task of searching for video more complicated. Video... more

The paper focuses on the algorithms of the event detection in content-based video retrieval. Video has a complex structure and can express the same idea in different ways. This makes the task of searching for video more complicated. Video titles and text descriptions cannot give the whole information about objects and events in the video. This creates a need for content-based video retrieval. There is a semantic gap between low-level video features, that can be extracted, and the users’ perception. The task of event detection is reduced to the task of video segmentation. Complex content-based video retrieval can be regarded as the bridge between traditional retrieval and semantic-based video retrieval. The properties of video as a time series are described. Introduced the concept of anomalies in the video. A method for event detection based on comparing moving averages with windows of different sizes is proposed. According to the classification given at the beginning of this article, our method refers to statistical methods. It differs from other methods with low computational complexity and simplicity. The video stream processing language is proposed for function-based description of video handling algorithms. So, our method is formulated in the form of a declarative description on an interpreted programming language. Unfortunately, most of the existing video processing methods use exclusively imperative approach, which often makes understanding more difficult. Examples of the use of this language are given. Its grammar is described too. As shown by experiments, the implementation of the proposed video events retrieval method, unlike their counterparts, can work for video streams too with a real-time and potentially infinite frame sequences. Such advantages within low computational requirements make implementation of the method helpful in aviation and space technology. The algorithm has some disadvantages due to necessity parameter selection for particular task classes. The theorem on near-duplicates of video is formulated at the end of the article. It asserts the near-duplicate videos express the same sequence of phenomena.

Gel electrophoresis (GE) is a process of DNA, RNA and protein molecules separation using electric field applied to a gel matrix. This paper describes the image processing techniques applied on GE image to segment the bands from their... more

Gel electrophoresis (GE) is a process of DNA, RNA and protein molecules separation using electric field applied to a gel matrix. This paper describes the image processing techniques applied on GE image to segment the bands from their background. A few pre-processing steps are applied on the image prior to the segmentation technique for the purpose of removing noise in the image. Multilevel thresholding using Otsu method based on Firefly Algorithm is developed. The experimental results show that the Otsu-FA produced good separation of DNA bands and its background.

In an image classification system based on deep learning, a training dataset is a set of labelled images and is often composed of a large number of images. Image labelling tool is usually used to facilitate in creating the training... more

In an image classification system based on deep learning, a training dataset is a set of labelled images and is often composed of a large number of images. Image labelling tool is usually used to facilitate in creating the training dataset used by the classifier during the learning phase. This paper presents a new image labelling tool called CrackLabel that can automatically label the cracks in the asphalt pavement images. A specially designed image thresholding method called the Global and Lower Quartile Average Intensity (GLQAI) method is utilised. In this study, the training dataset is developed by using real pavement images that resized to 1024×768 resolution. First, crack images are automatically segmented into 768 small patches with 32×32 resolution (pixel). Then, a threshold-based method is applied to automatically segment these patches into two classes which are crack and non-crack patches. The image thresholding method based on the average of global average intensity (GAI) and lower quartile intensity (LQI), namely GLQAI is proposed for this task. Next, the labelling process is performed by assigning patches associated with the crack and background into the crack and non-crack folder, respectively. Finally, the performance of CrackLabel is benchmarked by comparing the results with the manual label crack images by human experts, and three commonly used thresholding methods; Otsu, Kapur and Kittler-Illingworth thresholding. Experimental results show that the proposed thresholding method achieved the best classification rate among various thresholding methods with 94.50%, 93.60% 94.00% and 94.05% for recall, precision, accuracy, and F-score respectively. In conclusion, it is observed that the proposed method using the newly threshold algorithm is very effective in label images into the crack and non-crack patches to maximize the training performance.

There are great deals of consumer photographs which are affected by red-eye artifacts and arise frequently when shooting with flash. In this paper, a new technique is proposed to solve this problem. The proposed technique starts by... more

There are great deals of consumer photographs
which are affected by red-eye artifacts and arise frequently
when shooting with flash. In this paper, a new technique is
proposed to solve this problem. The proposed technique
starts by detecting the skin-like regions using an optimized
pixel-based neuro-fuzzy processing; morphological operations
are then used to discard the extra areas after crossing
the threshold. Once the skin regions are detected, five new
features including geometric and color metrics are proposed
to enhance the classification accuracy of the red-eye
artifacts. After that, another optimized neuro-fuzzy classifier
is employed to classify the red-eye regions by using the
presented features. Final result is achieved by a definite
syntax between skin and red-eye regions, and then, a
simple correction method is used to correct the detected
regions. Finally, a comparison is performed among the
proposed method toward the other popular procedures and
also a simple neuro-fuzzy. Final results showed the high
performance of the proposed method.

Blood detection process is still done with the help of laboratories that requires precision and sometimes makes errors to read because of the limitations of the human eye. Therefore, we need an automation process that can help human work... more

Blood detection process is still done with the help of laboratories that requires precision and sometimes makes errors to read because of the limitations of the human eye. Therefore, we need an automation process that can help human work to perform blood type analysis. In this study the method used to support the ABO method is the method of component labeling. Component labeling is selected because this method can provide initials or labels and provide pixel area information on a detected image object, so this method is suitabel for analyzing agglutination in blood samples. The results of the 24 obtained samples of blood samples were 100% samples can be analyzed correctly with the provision of the preparation sampling is above the threshold of 80 pixels, and the base color of the object is white.

Multi-level image thresholding is an important aspect in many image processing and computer vision applications. In the last decade, many fuzzy based image thresholding techniques have been proposed. In this article a new method for... more

Multi-level image thresholding is an important aspect in many image processing and computer vision applications. In the last decade, many fuzzy based image thresholding techniques have been proposed. In this article a new method for multi-level image thresholding is proposed using Type II Fuzzy sets. A new entropy measure is defined which is maximized to obtain the optimal thresholds for an image. As the number of thresholds increases, exhaustive search appears to be very time consuming. So, Differential Evolution (DE), a meta-heuristic algorithm, is used for fast selection of optimal thresholds. The proposed algorithm is compared with a fuzzy entropy based algorithm using image quality assessment measures Feature Similarity Index Measurement (FSIM) and Gradient Similarity Measurement (GSM). The use of DE is also justified by comparing it with other modern state-of-art algorithms like Gravitational Search Algorithm (GSA), Particle Swarm Optimization (PSO) and Genetic Algorithm (GA).

Image thresholding considered as a popular method for image segmentation. So far, many approaches have been proposed for image thresholding. Maximum entropy thresholding has been widely applied in the literature. This paper proposes a... more

Image thresholding considered as a popular
method for image segmentation. So far, many approaches have
been proposed for image thresholding. Maximum entropy
thresholding has been widely applied in the literature. This paper
proposes a multilevel image thresholding (MECOAT) using
cuckoo optimization algorithm (COA). COA is a new naturebased optimization algorithm which is inspired by a bird named
cuckoo. This algorithm is based unusual egg laying and breeding
of cuckoos. MECOAT tries to maximize entropy criterion. Three
different algorithms are compared with MECOAT algorithm:
particle swarm optimization, genetic algorithm, and bat
algorithm. Experimental results indicate that MECOAT
presents better results in terms of fitness value, peak signal to
noise ratio (PSNR) and robustness in most cases.

Thresholding is a fast, popular and computationally inexpensive segmentation technique that is always critical and decisive in some image processing applications. The result of image thresholding is not always satisfactory because of the... more

Thresholding is a fast, popular and computationally inexpensive segmentation technique that is always critical and decisive in some image processing applications. The result of image thresholding is not always satisfactory because of the presence of noise and vagueness and ambiguity among the classes. Since the theory of fuzzy sets is a generalization of the classical set theory, it has greater flexibility to capture faithfully the various aspects of incompleteness or imperfectness in information of situation. To overcome this problem, in this paper we proposed a two-stage fuzzy set theoretic approach to image thresholding utilizing the measure of fuzziness to evaluate the fuzziness of an image and to determine an adequate threshold value. At first, images are preprocessed to reduce noise without any loss of image details by fuzzy rule-based filtering and then in the final stage a suitable threshold is determined with the help of a fuzziness measure as a criterion function. Experimental results on test images have demonstrated the effectiveness of this method.

Multi-level image thresholding is an important aspect in many image processing and computer vision applications. In the last decade, many fuzzy based image thresholding techniques have been proposed. In this article a new method for... more

Multi-level image thresholding is an important aspect in many image processing and computer vision applications. In the last decade, many fuzzy based image thresholding techniques have been proposed. In this article a new method for multi-level image thresholding is proposed using Type II Fuzzy sets. A new entropy measure is defined which is maximized to obtain the optimal thresholds for an image. As the number of thresholds increases, exhaustive search appears to be very time consuming. So, Differential Evolution (DE), a meta-heuristic algorithm, is used for fast selection of optimal thresholds. The proposed algorithm is compared with a fuzzy entropy based algorithm using image quality assessment measures Feature Similarity Index Measurement (FSIM) and Gradient Similarity Measurement (GSM). The use of DE is also justified by comparing it with other modern state-of-art algorithms like Gravitational Search Algorithm (GSA), Particle Swarm Optimization (PSO) and Genetic Algorithm (GA).

The paper presents real time speckle de-noising based on activity computation algorithm and wavelet transform. Speckles arise in an image when laser light is reflected from an illuminated surface. The process involves detection of... more

The paper presents real time speckle de-noising based on activity computation algorithm and wavelet
transform. Speckles arise in an image when laser light is reflected from an illuminated surface. The process
involves detection of speckles in an image by obtaining a number of frames of the same object under
different illumination or angle and comparing the frames for the granular computation and de-noising the
same on presence of greater activity index. The project can be implemented in FPGA (Field Programmable
Gate Array) technology. The results can be shown that the used activity computation algorithm and wavelet
transform has better accuracy in the process of speckle detection and de-noising.

In an image classification system based on deep learning, a training dataset is a set of labelled images and is often composed of a large number of images. Image labelling tool is usually used to facilitate in creating the training... more

In an image classification system based on deep learning, a training dataset is a set of labelled images and is often composed of a large number of images. Image labelling tool is usually used to facilitate in creating the training dataset used by the classifier during the learning phase. This paper presents a new image labelling tool called CrackLabel that can automatically label the cracks in the asphalt pavement images. A specially designed image thresholding method called the Global and Lower Quartile Average Intensity (GLQAI) method is utilised. In this study, the training dataset is developed by using real pavement images that resized to 1024×768 resolution. First, crack images are automatically segmented into 768 small patches with 32×32 resolution (pixel). Then, a threshold-based method is applied to automatically segment these patches into two classes which are crack and non-crack patches. The image thresholding method based on the average of global average intensity (GAI) and lower quartile intensity (LQI), namely GLQAI is proposed for this task. Next, the labelling process is performed by assigning patches associated with the crack and background into the crack and non-crack folder, respectively. Finally, the performance of CrackLabel is benchmarked by comparing the results with the manual label crack images by human experts, and three commonly used thresholding methods; Otsu, Kapur and Kittler-Illingworth thresholding. Experimental results show that the proposed thresholding method achieved the best classification rate among various thresholding methods with 94.50%, 93.60% 94.00% and 94.05% for recall, precision, accuracy, and F-score respectively. In conclusion, it is observed that the proposed method using the newly threshold algorithm is very effective in label images into the crack and non-crack patches to maximize the training performance.

Edges detection of digital images is used in a various fields of applications ranging from real-time video surveillance and traffic management to medical imaging applications. Most of the classical methods for edge detection are based on... more

Edges detection of digital images is used in a various fields of applications ranging from real-time video surveillance
and traffic management to medical imaging applications. Most of the classical methods for edge detection are based on the first and
second order derivatives of gray levels of the pixels of the original image. These processes give rise to the exponential increment
of computational time. This paper shows the new algorithm based on both the Tsallis entropy and the Shannon entropy together for
edge detection using split and merge technique. The objective is to find the best edge representation and minimize the computation
time. A set of experiments in the domain of edge detection are presented. An edge detection performance compared to the previous
classic methods, such as Canny, LOG, and Sobel. Analysis show that the effect of the proposed method is better than those methods in
execution time and also is considered as easy implementation