An adaptive thresholding algorithm based on edge detection and morphological operations for document images

A vast number of historical and badly degraded document images can be found in libraries, public, and national archives. Due to the complex nature of different artifacts, such poor quality documents are hard to read and to process. In this paper, a novel adaptive binarization algorithm using ternary entropy-based approach is proposed. Given an input image, the contrast of intensity is first estimated by a grayscale morphological closing operator. A double-threshold is generated by our Shannon entropy-based ternarizing method to classify pixels into text, near-text, and non-text regions. The pixels in the second region are relabeled by the local mean and the standard deviation. Our proposed method classifies noise into two categories which are processed by binary morphological operators, shrink and swell filters, and graph searching strategy. The method is tested with three databases that have been used in the Document Image Binarization Contest 2009 (DIBCO 2009), the Handwriting Document Image Binarization Contest 2010 (H-DBCIO 2010), and the International Conference on Frontier in Handwriting Recognition 2010 (ICFHR 2010). The evaluation is based upon nine distinct measures. Experimental results show that our proposed algorithm outperforms other state-of-the-art methods.

Because of the different types of document degradation such as uneven illumination, image contrast variation and bleeding-through, binarization for degraded document images is still an enormous challenge for all scholars. This paper presents a new binarization method for degraded document images. The proposed algorithm focuses on the differences of image grayscale contrast in different areas. Firstly, theory of quadtree is used to divide areas adaptively. Secondly, various contrast enhancements are selected to adjust local grayscale contrast for different contrast areas. Lastly, the frequency of gray value is utilized to calculate threshold. The proposed algorithm was tested on the datasets of Document Image Binarization Contest (DIBCO) (DIBCO 2009, H-DIBCO 2010, DIBCO 2011, H-DIBCO 2012). Compared with other five classical algorithms, the binaried images using proposed algorithm gain the highest F-measure and PSNR.

Binarization is an important step in reading text documents automatically through optical character recognition. Old document images often suffer from degradations that make their binarization a challenging task. In this paper, a new binarization technique for degraded document images is presented. The proposed technique is based on active contours evolving according to intrinsic geometric measures of the document image. The image contrast that is defined by the local image maximum and minimum is used to automatically generate the initialization map of our active contour model; an average thresholding is also used to produce the final delineation and binarization. The proposed implementation benefits from the level set framework, which allows the simultaneous application of a large variety of forces at the stroke–background interface. Our binarization method involves the combination of those forces in a specific way. The efficiency of the proposed method is shown on both recent and historical document images of the Document Image Binarization Contest (DIBCO) datasets that include different types of degradations. The results are compared to a number of known techniques from the literature.

One of the most significant current discussions in image processing is a document analysis. Now, many types of document database were established in order to address the issue of binarization effectiveness. In this paper, a comprehensive review of the document database was presented. Review based on an image from Document Image Binarization Contest (DIBCO) from 2013 to 2017 which consists of handwritten and printed image. The best algorithm for each year is discussed and analyzed. Based on the results, the technique using background estimation and stroke edges is better performance for the overall database. Besides, the method using the combination of Laplacian operator and canny edge detection also shows the successful result, especially in the printed image. Implications of the review give the direction for future binarization approach developments.

Edge detection and recognition is one of the most critical procedures in image processing and pattern recognition. Traditional Canny algorithm has some advantages, such as simple and fast execution times. It is not good enough when traditional Canny algorithm is applied in complex background images for objects edge detection. It is sensitive to noise and low location accuracy. To solve the shortcomings of traditional Canny algorithm, we propose an improved edge detection and recognition algorithm. The proposed edge detection algorithm can remove the influence of complex background images in the process of edge detection and characters segmentation. The effectiveness of the proposed algorithm is demonstrated by the experimental results. The proposed algorithm can eliminate the complex background of credit card and detect the meaningful edges of its numbers. The experimental results show the improved algorithm can obtain accurate edge position and good segmentation results.

Edge detection is an important work for object recognition and is also an essential pre-processing step in image segmentation and visual analysis. This paper deeply studies the edge detection methods of the noisy images and concentrates on the mathematical morphology methods. By analyzing and studying the theory of mathematical morphology, the paper constructs edge detection operations and analyzes the specialties of the operator and the structure elements. Based on this, the paper proposes a new method of edge detection using mathematical morphology and image fusion. The operations can obtain clear and exact edge of the noisy images. By simulation and comparing with the traditional edge detection operations, the proposed method is more effective on noise restraining and retaining the image details.

Automatic Image Analysis, Image Classification, Automatic Object Recognition are some of the aspiring research areas in various fields of Engineering. Many Industrial and biological applications demand Image Analysis and Image Classification. Sample images available for classification may be complex, image data may be inadequate or component regions in the image may have poor visibility. With the available information each Digital Image Processing application has to analyze, classify and recognize the objects appropriately. Pre-processing, Image segmentation, feature extraction and classification are the most common steps to follow for Classification of Images. In this study we applied various existing edge detection methods like Robert, Sobel, Prewitt, Canny, Otsu and Laplacian of Guassian to crab images. From the conducted analysis of all edge detection operators, it is observed that Sobel, Prewitt, Robert operators are ideal for enhancement. The paper proposes Enhanced Sobel operator, Enhanced Prewitt operator and Enhanced Robert operator using morphological operations and masking. The novelty of the proposed approach is that it gives thick edges to the crab images and removes spurious edges with help of m-connectivity. Parameters which measure the accuracy of the results are employed to compare the existing edge detection operators with proposed edge detection operators. This approach shows better results than existing edge detection operators.

The iris is a part of the human anatomy that can be used as a biometric identifier. Data obtained from the iris can be converted into information through iris image processing, and in order to obtain accurate iris pixel results, an edge detection operator is required that can provide detailed and good image quality effects. In this research, a comparative analysis of the Canny, Sobel, Prewitt and Roberts edge detection operators was carried out on iris images. The purpose of performing a comparative analysis of edge detection methods is to compare the detection results of each edge detection operator on iris recognition detected by each operator. The results of the comparison of edge detection methods using precision tables can be analyzed to show that the Canny edge detection operator provides better, smoother and sharper edge results in actual edge point detection, namely 0.357867, while Sobel =, 0.210212, Prewitt = 0.212452 and Roberts = 0.279196. From these results it can be concluded that the edge detection results provided by Sobel and Prewitt are less sharp and sensitive to noise, and the comparison results can vary depending on the intensity of the image and the image object being compared.

According to the theory of mathematical morphological, edge detection operators and characteristics of wood decay image, a multi-structure element multi-scale edge detection algorithm based on mathematical morphology is proposed. The image is filtered by an alternative-order morphological corrosion-expansion filter with a multi-scale element, and the edge information is obtained using multi-structure elements open-close operation. Canny operator is used to extract the edge of the decay image. Experimental results show that the proposed algorithm is insensitive to noise and is efficient in edge detection.

Document image binarization has been a long standing problem for unconstrained document images. Although various thresholding algorithms have been developed over the years, problems associated with strong noise, complex patterns, poor contrast, and variable modalities in gray-scale histograms still limit the performance of document image analysis systems. Given the unpredictable nature of these image attributes, few thresholding algorithms work consistently well for document image binarization. This dissertation presents texture feature based thresholding algorithms to address these difficulties. The philosophy of our thresholding approach is that the texture domain knowledge of document images is important to judge the binarization quality and thus guide the binarization process; that is, suitably defined texture features of document images can be used to assist the optimal threshold selection. Our thresholding scheme consists of three steps. First, candidate thresholds are produced through the iterative use of Otsu's algorithm. Second, texture features associated with each candidate threshold are extracted from the run-length histogram of the accordingly binarized image. Third, the optimal threshold is selected so that the most desirable document texture features are preserved. This thresholding scheme was implemented in both global and adaptive modes. With our program design the algorithms require only one image scan pass, facilitating their hardware implementation for a commercial system. Experimental results with 9000 machine printed address blocks from an unconstrained US mail stream demonstrated that over 99.6% of the images were well binarized by our thresholding method, which are appreciably better than those obtained by existing thresholding techniques. Also a system run with 500 difficult mail address blocks showed that an 8.1% higher character recognition rate was achieved by our algorithm in comparison to that by Otsu's algorithm.

The technique core of grain reserves automatical supervision and audit system which based on video is to identify the grain warehouse scene video, and accurately gets the sum of grain quantity. The key to identifying the quantity is the shape of package, and the key to identifying shape is processing and describing the boundary of package. Based on a lot of research and experiment on the edge detection operators, this article select the canny operator and chain code to process and describe the boundary of package. Aiming at the boundary is not absolute connectivity, the closure operation of Mathematical Morphology is introduced to do pretreatment on binary image of packaged grain. Finally the boundary is absolute connectivity. Experiments show that the proposed method enhances the anti-jamming and robustness of edge detection, and satisfy precision request of packaged grain quantify recognition.

A novel approach of combined edge detection and segmentation for tool wear measurement in machining

This study aims to identify chicken egg embryos with the concept of image processing. This concept uses input and output in images. Thus the identification process, which was originally carried out using manual observation, was developed by computerization. Digital images are applied in identification by various image preprocessing, image segmentation, and edge detection methods. Based on these three methods, image processing has three processes: image grayscaling (convert to a grayscale image), image adjustment, and image enhancement. Image adjustment aims to clarify the image based on color correction. Meanwhile, image enhancement improves image quality, using histogram equalization (HE) and Contrast Limited Adaptive Histogram Equalization methods (CLAHE). Specifically for the image enhancement method, the CLAHE-HE combination is used for the improvement process. At the end of the process, the method used is edge detection. In this method, there is a comparison of various edge detection operators such as Roberts, Prewitt, Sobel, and canny. The results of edge detection using these four methods have the SSIM value respectively 0.9403; 0.9392; 0.9394; 0.9402. These results indicate that the SSIM values ​​of the four operators have the same or nearly the same value. Thus, the edge detection method can provide good edge detection results and be implemented because the SSIM value is close to 1.00 (more than 0.93). Image segmentation detected object (egg and embryo), and the continued process by edge detection showed clearly edge of egg and embryo.

Edge detection is a fundamental step in many machine vision or image processing applications and systems. The importance of edge detection increases as one seeks to increase the level of automation in the image processing system. The paper reports an edge detection operator which is fast in application to grey scale images and is sensitive to 'difficult' edges but not sensitive to artifacts such as scanner interlacing artifacts. The edge detection operator presented is simple but provides good detection of edges and clean and continuous edges across most of the image.

On the basis of Canny operator on image processing, The edge extraction of the fuzzy droplet images is carried out by combination of removing a small target and morphological open operation .First, Use edge detection operator to detect the image edge preliminary, and then call remove a small target which belongs to MATLAB internal function to filtering the results of the edge detection, and finally with morphological operations for final processing.The results showed that: the combination of Canny operator, open operation and remove a small target works much better than the classical Canny operator.