Character Contour Research Articles

Low contrast stamped dates recognition for pill packaging boxes based on YOLO-SFD and image fusion

Dates sealed by embossed stamps (stamped dates) on pill packaging boxes are crucial for people to notice the expiration dates. Thus, manufacturers must ensure the accuracy of stamped dates on the pill packaging boxes. However, the low contrast between the stamped dates and the surface of the container and the lack of clear character outlines often lead to light interference, which hampers the stamped dates detections by various deep learning models. This article presents a method for detecting stamped characters that combines YOLO-Shallow Feature Detection (YOLO-SFD) and image fusion. YOLO-SFD enhances YOLOv8 by introducing a Shallow Feedback Feature Pyramid Network (SF-FPN) that includes shallow feature paths and feedback paths for the original input. This enables the model to pay more attention to the shallow features, which include a more detailed character contour. Secondly, this paper presents a lightweight convolutional structure to enhance the model's portability without sacrificing accuracy. Experimental results indicate that SF-FPN outperforms the original feature pyramid network in terms of accuracy and model size. On the stamped date dataset, YOLO-SFD achieves an average accuracy of 99.02 %, 2.57 % higher than the original model, with 29 % fewer parameters. In addition, a 1.5 % mAP improvement is achieved on the Street View House Numbers Dataset. This shows that this method can better fulfill the requirements of pill packaging box stamped date detection and provides new solutions and ideas for related character detection or low contrast image detection.

Cartoon copyright recognition method based on character personality action

Aiming at the problem of cartoon piracy and plagiarism, this paper proposes a method of cartoon copyright recognition based on character personality actions. This method can be used to compare the original cartoon actions with the action characteristics of pirated or copied cartoons to identify whether there is piracy or plagiarism. Firstly, an image preprocessing scheme for character extraction is designed. GrabCut interactive image segmentation algorithm was used to obtain cartoon characters, and then binarization and morphological processing were performed on the results. Secondly, a feature extraction scheme based on character profile, moving character and character pose is designed. By extracting the perimeter and area of the character contour, the length-to-width ratio of the smallest rectangle and the inclination angle of the contour, the character contour features are obtained. The three-dimensional coordinates are established by the central point position of the cartoon character in the two-dimensional image and the change of the character's zoom in and out, and the character's motion angle characteristics are calculated. By skeletonizing a character to obtain the pose characteristics, and using deburring operation to remove redundant branches, then extract the skeleton joint angle information. Finally, feature fusion is performed on the extracted features. The experimental results show that the proposed method breaks the limitation of the conventional single feature based recognition, and can better extract the character features including contour feature, motion feature and pose feature through multi-feature based extraction, so as to protect the cartoon copyright.

Arabic Handwritten Recognition by using His Features

The present study is a contribution in the filed of Arabic character recognition. The first step is to enter an image from a scanner, and then some special processes are done on the image like (smoothing and thinning and resizing) before continuous to segmentation phase. Then modified moment invariant computed using the shape boundary of the character only is utilized as features.Also this study is concerned with the recognition of handwritten Arabic character drawn on a graphic tablet. At first feature that are suitable for recognition are proposed. Feature that are found to be independent of the writer style are represented as a list (vector) of integer values.The designed system in general view is an Arabic text recognition system basically includes a segmentation stage in order to recognize handwritten Arabic words. The segmentation process is completely based on tracing the outer of given word and calculating the output distance between the extreme points of intersection of the contour with vertical line. At the output of the segmentation stage the cursive word is presented as a sequence of isolated character contour.

Handwritten English Character Recognition and translate English to Devnagari Words

In our proposed work we will accept the challenges of recognizing the words and we will work to win the challenge. The handwritten document is scanned using a scanner. The image of the scanned document is processed victimization the program. Each character in the word is isolated. Then the individual isolated character is subjected to “Feature Extraction” by the Gabor Feature. Extracted features are passed through KNN classifier. Finally we get the Recognized word. Character recognition is a process by which computer recognizes handwritten characters and turns them into a format which a user can understand. Computer primarily based pattern recognition may be a method that involves many sub process. In today’s surroundings character recognition has gained ton of concentration with in the field of pattern recognition. Handwritten character recognition is beneficial in cheque process in banks, form processing systems and many more. Character recognition is one in all the favored and difficult space in analysis. In future, character recognition creates paperless environment. The novelty of this approach is to achieve better accuracy, reduced computational time for recognition of handwritten characters. The proposed method extracts the geometric features of the character contour. These features are based on the basic line types that forms the character skeleton. The system offers a feature vector as its output. The feature vectors so generated from a training set, were then used to train a pattern recognition engine based on Neural Networks so that the system can be benchmarked. The algorithm proposed concentrates on the same. It extracts totally different line varieties that forms a specific character. It conjointly also concentrates on the point options of constant. The feature extraction technique explained was tested using a Neural Network which was trained with the feature vectors obtained from the proposed method.

An Attack on Hollow CAPTCHA Using Accurate Filling and Nonredundant Merging

ABSTRACTAs one of the effective access control mechanism, CAPTCHA can provide privacy protection and multimedia security for big data. In this paper, an attack on hollow CAPTCHA using accurate filling and nonredundant merging is proposed. Firstly, a thinning operation is introduced to repair character contour precisely. Secondly, an inner-outer contour filling algorithm is presented to acquire solid characters, which only fills the hollow character components rather than noise blocks. Thirdly, the segmentation to the solid characters produces mostly individual characters and only a small number of character components. Fourthly, a minimum-nearest neighbor merging algorithm is proposed to obtain individual characters without redundancy. Lastly, the convolutional neural network (CNN) is applied to acquire the final recognition results. The experimental results based on the real CAPTCHA data sets show that comparing with the existing attack methods on hollow CAPTCHA, the proposed method has higher success rate and superior efficiency.

Walter the Chancellor on Ilghazi and Tughtakin: a prisoner’s perspective

ABSTRACTThis article concerns two leading Turkish rulers, active in the Near East during the crusading era: Tughtakin of Damascus and Ilghazi of Mardin. They were important commanders, but the surviving sources create difficulties when outlining the contours of characters and cultural perspectives. Muslim authors typically present them as idealised Islamic rulers and yet it is difficult to accept such stereotyped portraits. This article sheds new light on these men, seeking to understand how far they had transitioned from the steppe culture of their forefathers into a more distinctively Islamic mould. It focuses in particular on the Antiochene chronicle written by Walter the Chancellor. He witnessed both rulers at first hand when he was their prisoner in Aleppo in 1119, an experience which left him deeply scarred. This is tainted evidence, yet it will be shown that many of Walter’s observations also provide invaluable insights that deserve to be taken seriously.

Improved Line Segmentation Framework for Sundanese Old Manuscripts

Line segmentation can be a useful process for further text segmentation. There are some certain line segmentation framework that use binarization method as an initial step. But binarization process is still facing a major challenge, especially on old document palm-leaf manuscripts. As the quality of the image has varying degrees of noises in the non-text region. Seam Carving method, one of line segmentation methods that uses binarization-free approach, can be an alternative solution. However, this method can separate the incorrect text line on small element text located at the bottom or at the top of a main character contour. Therefore, an improvement on line segmentation framework is proposed by using hybrid binarization and its implemented on the smallest energy function to separate out the text-lines. The proposed framework have been evaluated on 44 Sundanese old manuscript images that consist of true color and binary images. The evaluation matrix shows that this framework can improve Niblack binarization process up to 50%. In addition, our framework does not only generate the number of text-lines to come near to the number of target lines, but it also can separate the text-lines well on small element text. Overall, the expected result can in the end be produced from the proposed line segmentation framework.

Efficient image compression and decompression algorithms for OCR systems

This paper presents an efficient new image compression and decompression methods for document images, intended for usage in the pre-processing stage of an OCR system designed for needs of the ?Nikola Tesla Museum? in Belgrade. Proposed image compression methods exploit the Run-Length Encoding (RLE) algorithm and an algorithm based on document character contour extraction, while an iterative scanline fill algorithm is used for image decompression. Image compression and decompression methods are compared with JBIG2 and JPEG2000 image compression standards. Segmentation accuracy results for ground-truth documents are obtained in order to evaluate the proposed methods. Results show that the proposed methods outperform JBIG2 compression regarding the time complexity, providing up to 25 times lower processing time at the expense of worse compression ratio results, as well as JPEG2000 image compression standard, providing up to 4-fold improvement in compression ratio. Finally, time complexity results show that the presented methods are sufficiently fast for a real time character segmentation system.

Contour Restoration of Text Components for Recognition in Video/Scene Images.

Text recognition in video/natural scene images has gained significant attention in the field of image processing in many computer vision applications, which is much more challenging than recognition in plain background images. In this paper, we aim to restore complete character contours in video/scene images from gray values, in contrast to the conventional techniques that consider edge images/binary information as inputs for text detection and recognition. We explore and utilize the strengths of zero crossing points given by the Laplacian to identify stroke candidate pixels (SPC). For each SPC pair, we propose new symmetry features based on gradient magnitude and Fourier phase angles to identify probable stroke candidate pairs (PSCP). The same symmetry properties are proposed at the PSCP level to choose seed stroke candidate pairs (SSCP). Finally, an iterative algorithm is proposed for SSCP to restore complete character contours. Experimental results on benchmark databases, namely, the ICDAR family of video and natural scenes, Street View Data, and MSRA data sets, show that the proposed technique outperforms the existing techniques in terms of both quality measures and recognition rate. We also show that character contour restoration is effective for text detection in video and natural scene images.

Modeling Character Canvases from Cartoon Drawings

We introduce a novel technique for the construction of a 3D character proxy, or canvas , directly from a 2D cartoon drawing and a user-provided correspondingly posed 3D skeleton. Our choice of input is motivated by the observation that traditional cartoon characters are well approximated by a union of generalized surface of revolution body parts, anchored by a skeletal structure. While typical 2D character contour drawings allow ambiguities in 3D interpretation, our use of a 3D skeleton eliminates such ambiguities and enables the construction of believable character canvases from complex drawings. Our canvases conform to the 2D contours of the input drawings, and are consistent with the perceptual principles of Gestalt continuity, simplicity, and contour persistence. We first segment the input 2D contours into individual body-part outlines corresponding to 3D skeletal bones using the Gestalt continuation principle to correctly resolve inter-part occlusions in the drawings. We then use this segmentation to compute the canvas geometry, generating 3D generalized surfaces of revolution around the skeletal bones that conform to the original outlines and balance simplicity against contour persistence. The combined method generates believable canvases for characters drawn in complex poses with numerous inter-part occlusions, variable contour depth, and significant foreshortening. Our canvases serve as 3D geometric proxies for cartoon characters, enabling unconstrained 3D viewing, articulation, and non-photorealistic rendering. We validate our algorithm via a range of user studies and comparisons to ground-truth 3D models and artist-drawn results. We further demonstrate a compelling gallery of 3D character canvases created from a diverse set of cartoon drawings with matching 3D skeletons.

Triangulation Based Skeletonization and Trajectory Recovery for Handwritten Character Patterns

In this paper, we propose a novel approach for trajectory recovery. Our system uses a triangulation procedure for skeletonization and graph theory to extract the trajectory. Skeletonization extracts the polyline skeleton according to the polygonal contours of the handwritten characters, and as a result, the junction becomes clear and the characters that are touching each other are separated. The approach for the trajectory recovery is based on graph theory to find the optimal path in the graph that has the best representation of the trajectory. An undirected graph model consisting of one or more strokes is constructed from a polyline skeleton. By using the polyline skeleton, our approach accelerates the process to search for an optimal path. In order to evaluate the performance, we built our own dataset, which includes testing and ground-truth. The dataset consist of thousands of handwritten characters and word images, which are extracted from five handwritten documents. To show the relative advantage of our skeletonization method, we first compare the results against those from Zhang-Suen, a state-of-the-art skeletonization method. For the trajectory recovery, we conduct a comparison using the Root Means Square Error (RMSE) and Dynamic Time Warping (DTW) in order to measure the error between the ground truth and the real output. The comparison reveals that our approach has better performance for both the skeletonization stage and the trajectory recovery stage. Moreover, the processing time comparison proves that our system is faster than the existing systems.

Research on Automatic Identification of Substation Circuit Breaker Based on Shape Priors

High-pressure circuit breakers are very important and it undertakes the disconnection and connection control of high voltage transmission lines. It is one of the equipment of substation daily inspection. State of breakers are judged by open and close characters label, so a shape-prior active contour model to realize state automatic recognition of breaker images collected by inspection robot is presented in this paper. Shape-prior active contour model combines the shape information with CV model to build energy functional model, then set up initial position curve by a priori knowledge and drives the curve evolution in minimize energy functional process, the curve position is the character label contour when energy functional shows minimum. We do experiment for the algorithm on different images, demonstrate that the algorithm based on known character contour, have good segmentation results of circuit breaker in the image character recognition accuracy and applicability when the circuit breaker character is actually partial occlusion, local deformation, scale changes.

A License Plate Character Segmentation Method Based on Character Contour and Template Matching

In order to solve the problems of the cracked and adhesive characters of license plate caused by the plate frame, rivet, light intensity, a novel character segmentation method based on character contour and template matching was presented. In the proposed methodology, the license plate image contrast was enhanced by the adaptive gray stretch method. The cracked and adhesive characters were accurately extracted owing to the spatial scalability of the contour. Then the found characters were matched according to the adaptive templates. The characters were segmented once more by the best template and then residual characters were complemented and fake characters were removed. A large number of character segmentation experiments under different illumination conditions were made. The results show that the method has a strong robustness and practicability.

A Location Method for Multi-style License Plates Based on Character Classification

Abstract To locate the license plate exactly is a challenging task, especially for the license plates with complex backgrounds or shadows. Firstly, we use a multilevel local adaptive thresholding method instead of global thresholding methods to produce binary images under varying illuminations. Secondly, the connected contour analysis is applied to extract the main characters, and the false character contour regions are filtered out by the SVM classification method using PCA dimensionality reduction. Finally, we merge the remaining characters on the same line to extract candidate regions of the license plate. Experimental results show that the proposed method achieves higher accuracy, more acceptable and precise results. By using the data sets of the license plates in the USA and Europe, the method is shown to be suitable for multi-style license plates.

Text extraction from scene images by character appearance and structure modeling

In this paper, we propose a novel algorithm to detect text information from natural scene images. Scene text classification and detection are still open research topics. Our proposed algorithm is able to model both character appearance and structure to generate representative and discriminative text descriptors. The contributions of this paper include three aspects: (1) a new character appearance model by a structure correlation algorithm which extracts discriminative appearance features from detected interest points of character samples; (2) a new text descriptor based on structons and correlatons, which model character structure by structure differences among character samples and structure component co-occurrence; and (3) a new text region localization method by combining color decomposition, character contour refinement, and string line alignment to localize character candidates and refine detected text regions. We perform three groups of experiments to evaluate the effectiveness of our proposed algorithm, including text classification, text detection, and character identification. The evaluation results on benchmark datasets demonstrate that our algorithm achieves the state-of-the-art performance on scene text classification and detection, and significantly outperforms the existing algorithms for character identification.

ARABIC CHARACTER RECOGNITION USING MODIFIED FOURIER SPECTRUM (MFS) VS. FOURIER DESCRIPTORS

Fast Fourier transform (FFT) is used successfully in computing the Fourier descriptors which are used in object and character recognition. In this article, an Arabic character recognition algorithm using modified fourier spectrum (MFS) is presented. Ten descriptors are estimated from the Fourier spectrum of the character contour by subtracting the imaginary part from the real part (and not from the amplitude of the Fourier spectrum as is usually the case). Ten MFS descriptors are extracted and used for the recognition of Arabic characters. Experimental results using 10 MFS descriptors resulted in an average recognition rate of 95.9%. The analysis of the sparse matrix indicates that the major part of the errors is due to few similar characters. The new technique, based on MFS descriptors, was compared with the Fourier descriptors calculated from the amplitude of the FFT spectrum. Experimental results have shown that the MFS-based technique is faster to compute than the FFT-based technique. However, the Fourier descriptors, initially, have a better recognition rate than MFS descriptors (96.9% vs. 95.9%). Using the holes' and dots' features to resolve the problematic characters reduces the error rate of the MFS technique more than that of the Fourier descriptor technique. This article introduced MFS-based features that are faster to compute than Fourier descriptors and have fewer errors utilizing the dots and holes features of Arabic characters. Both techniques may be used in combination or in a multi-classifier system to enhance the Arabic recognition system rate.

Product development for Chinese calligraphy using reverse engineering and rapid prototyping

Chinese calligraphy is considered to be one of the most beautiful and meaningful patterns in the world. Calligraphy is an art dating back to the earliest day of Chinese history, and widely practised throughout ancient China even to recent days. Owing to the passage of time, many old carvings of stamp characters have gradually faded. How to preserve these old Chinese cultural artifacts will be some crucial issues for today. Reverse engineering (RE) and rapid prototyping (RP) technology are considered effective tools for product development. This research combines RE, grey prediction theory in pattern processing, geometric modeling for constructing the characters of Chinese calligraphy and RP for model making. First, the written Chinese calligraphy is scanned by a scanner. By using image processing, the contours of the Chinese characters can be detected. The contours for the characters then turn out to be point data which can be easily processed in any computer aided design (CAD) software by using B-Spline curves to fit the points. An example is demonstrated by writing a Chinese compound word ‘the fortune and treasure are coming’ to show the process. Finally, a RP model is fabricated to show various applications for the products in Chinese calligraphy pattern. By this research, the gap between the Chinese calligraphy in handicraft and digital virtual design can be realized. More usefully, with this research the aesthetic aspects in the characters can be preserved.

An investigation of the modified direction feature for cursive character recognition

This paper describes and analyses the performance of a novel feature extraction technique for the recognition of segmented/cursive characters that may be used in the context of a segmentation-based handwritten word recognition system. The modified direction feature (MDF) extraction technique builds upon the direction feature (DF) technique proposed previously that extracts direction information from the structure of character contours. This principal was extended so that the direction information is integrated with a technique for detecting transitions between background and foreground pixels in the character image. In order to improve on the DF extraction technique, a number of modifications were undertaken. With a view to describe the character contour more effectively, a re-design of the direction number determination technique was performed. Also, an additional global feature was introduced to improve the recognition accuracy for those characters that were most frequently confused with patterns of similar appearance. MDF was tested using a neural network-based classifier and compared to the DF and transition feature (TF) extraction techniques. MDF outperformed both DF and TF techniques using a benchmark dataset and compared favourably with the top results in the literature. A recognition accuracy of above 89% is reported on characters from the CEDAR dataset.

170Wavelet Features based On-line Recognition of Handwritten

On-line character recognition systems, usually, extract features like direction, curvature trajectory of the characters, pen-ups, velocity of the pen, etc., from the handwritten characters for recognition. Whereas, if wavelet features of characters are extracted, they represent combination of many of the conventional features and act as a simple novel candidate for character recognition. This paper reports the details of an on-line character recognition system developed by the authors, for the handwritten characters/words of Kannada, a National language of India, which employs the wavelet features of the character contour for recognition. The results obtained are most encouraging.

Rejection Criteria and Pairwise Discrimination of Handwritten Numerals Based on Structural Features

This paper presents a new structural method for the recognition of handwritten numerals. Contour shape features, such as convex arcs, concave arcs, line segments, end-point arcs and holes from the contours of numeric characters, are used to describe numeral characters. A new method of measuring the similarity between a sample and class is proposed. A two-stage recognition methodology is also presented, in which two rejection criteria are introduced. In the first stage of recognition, an input sample is given an identity or categorised as either first class or second class rejection, based on similarity measures between the input sample and each of the ten numeral classes. In the second stage of recognition, strategies are introduced to modify the structural description of the input sample if it is in first class rejection and a classifier focused on pairwise discrimination is applied if the input sample is in second class rejection. Experimental results indicate that the overall performance of the proposed method compares favourably with those achieved by other methods found in the literature.