توجه: محتویات این صفحه به صورت خودکار پردازش شده و مقاله‌های نویسندگانی با تشابه اسمی، همگی در بخش یکسان نمایش داده می‌شوند.
۱Farsi\Arabic Text Extraction from Video Images by Corner Detection
اطلاعات انتشار: ششمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۶
Video text information plays an important role in semanticbased video analysis, indexing and retrieval. In this paper, we proposed a novel Farsi text detection approach based on intrinsic characteristics of Farsi text lines, which is more robust to complex backgrounds and various font styles. First, by an edge detector operator, all the possible edges in vertical, horizontal, 45 and 135 degrees are extracted. Then, for extracting text strokes, some pre–processing such as dilation and erosion are done according to the font size. Afterward, by finding the edges cross points, corners map is extracted. To discard non–text corners and finding real font size, histogram analysis is done. After finding real font size, input image is rescaled and a new corner map is extracted. Finally, the detected candidate text areas undergo the empirical rules analysis to identify text areas and project profile analysis for verification and text lines extraction. Experimental results demonstrate that the proposed method is robust to font size, font colour, and background complexity.<\div>

۲Eroded Money Notes Recognition using Wavelet Transform
نویسنده(ها): ،
اطلاعات انتشار: ششمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۵
Process of bank checks and money notes play an important role in today commercial society. Usually automatic teller machines (ATM) have problems with eroded money notes. In this paper we proposed a new method for worn out Farsi money notes recognition using their texture content and wavelet transform. First, with the help of face detection algorithm, the obverse of the money note is separated from its reverse side. Then, central part of the money note, containing texture is extracted. Finally, wavelet transform is applied to this region of interest (ROI) to extract some features. Some distance measures are utilized to classify the input money note into predefined groups according to minimum distance. To increase accuracy of the system, in the post processing step, we used courtesy amount of the money note and template matching technique. The experimental results have shown that system performance is 80% for eroded money notes recognition.<\div>

۳Machine Printed Farsi\Arabic Sub–words Retrieval by Shape Signatures
نویسنده(ها): ،
اطلاعات انتشار: ششمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۶
This paper focuses on shape description for machine printed Farsi\Arabic subwords retrieval. Fourier descriptor (FD) has been used frequently for shape retrieval applications. In this paper we proposed a simple and effective FD based technique for subwords retrieval. In this method, the small number of global parameters is used to eliminate dissimilar subwords. To investigate the efficiency of the proposed method, it is compared with six common FD signatures on a database including Farsi subwords of 4 fonts and 3 sizes. Experimental results show that the proposed method outperforms the others<\div>

۴Performance Enhancement of PCA–based Face Recognition System via Gender Classification Method
نویسنده(ها): ،
اطلاعات انتشار: ششمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۶
In this paper, we demonstrate that gender estimation technique can increase the accuracy of a face recognition system. If the gender of the input image can be estimated correctly before its recognition and compared only with images of the same sex, errors between males and females during recognition step can be eliminated. Consequently, the accuracy will be boosted. Principal Component Analysis (PCA) face recognition system based on single image has been used in our experiment. To be compatible with this recognizer, the proposed gender estimation algorithm uses also a non–training procedure. A part of FERET database including 292 male and 264 female images has been used. Experimental results show 7% accuracy enhancement for PCA recognition system in the presence of gender estimation.<\div>

۵Watermarking in Farsi\Arabic binary document images using fractal coding
نویسنده(ها): ،
اطلاعات انتشار: هشتمین کنفرانس انجمن رمز ایران، سال
تعداد صفحات: ۶
This paper presents a novel watermarking method based on fractal theory. In the proposed method, information is embedded into binary document images. First, host image is coded by the proposed fractal coding method which is designed particularly for binary images. To insert the watermark uniformly over the entire host image, only some of Range segments with certain conditions are selected. Then, the watermark is added to the number of ones in the fractal code of selected Range segments. Finally, the output image is obtained by the fractal decoding procedure. Experimental results show that the output image quality of the proposed methods is acceptable to human eyes. In addition, empirical results show that the proposed fractal based watermarking is robust to the common attacks.<\div>

۶Performance Comparison between Zernike Moment Invariant and Fractal Codes features in the Application of Zip Code Recognition using RBF Neural Network
اطلاعات انتشار: ششمین کنفرانس سراسری سیستم های هوشمند، سال
تعداد صفحات: ۶
This paper presents a system for off–line recognition of segmented (isolated) handwritten Farsi\Arabic characters and numerals. We have used Zernike Moment Invariant and Fractal Codes as two different kinds of features in this system. Also Radial Basis Function (RBF) neural network that is used for many engineering problems and pattern recognition tasks has been employed in this work. Simulation results on our database, which were gathered from various people with different ages and different educational backgrounds, indicate that the ZMI and fractal codes are suitable features for segmented handwritten Farsi\Arabic characters and numerals recognition and the best performances of this system are 91.5% and 92.8% for characters and numerals recognition respectively<\div>

۷Twins Facial Similarity Impact on Conventional Face Recognition Systems
نویسنده(ها): ،
اطلاعات انتشار: نوزدهمین کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۶
Variations in pose, expression, aging and disguise are considered as basic challenges in face recognition systems and several standard databases have been built to address these challenges. Twins face recognition, on the other hand, has not yet been studied because there is no database which includes face images of twins. In this paper we present a new unconstrained face database which contains 3,804 face images of 1,902 pairs of twins. These images were collected from different twins’ festivals from the World Wide Web. We provided an analytical study to experiment the impacts of twins facial similarity on different face recognition algorithms. The results show that the algorithms are unable to meet an acceptable rate of identification performance on twins face database. In this paper descriptions of the database such as development process, organization as well as statistic information are also depicted in details<\div>

۸FARSI\ARABIC TEXT EXTRACTION FROM VIDEO IMAGES
اطلاعات انتشار: نوزدهمین کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۶
Video text information plays an important role in semantic–based video analysis, indexing, and retrieval. In this paper we proposed a novel text detection approach based on intrinsic characteristics of Farsi text lines, which is more robust to complex backgrounds and various font styles. First, a Gaussian pyramid with two levels is created from input I–frame images. Then, corner histogram analysis is done. Input image is divided into some macro blocks from which features are extracted and fed into support vector machine (SVM) classifier to classify them into text and nontext areas. Finally, the detected candidate text areas undergo some empirical rules to refine text localization stage results. Experimental results demonstrate that the proposed approach can be used as an automatic text detection system, which is robust to font size, font colour, and background complexity.<\div>

۹Face Verification using Second Orders Polynomial Correlation Filters
نویسنده(ها): ،
اطلاعات انتشار: بیستمین کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۵
Face verification is a critical task for individual authentication, e–commerce applications and security purpose. Correlation filtering has recently been reintroduced to thefacial verification domain. In This paper we utilize polynomial correlation filter (PCF) based on unconstrained minimum average correlation energy (UMACE).The performance ofUMACE–PCF is evaluated using YALE B database. A comparison of verification performance between the secondorders of UMACE–PCF and UMACE filter is also presented<\div>

۱۰Font Recognition Using Variogram Fractal Dimension
نویسنده(ها): ،
اطلاعات انتشار: بیستمین کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۶
This paper is dealing with font recognition problem in Farsi, Arabic, and English documents. It considers font recognition as texture identification task and the extractedfeatures are independent of document content. The proposed method is based on one of the fractal dimension techniques which is called Variogram Analysis. The average recognitionrates using RBF, and KNN classifiers are respectively %95.5, %96 for Farsi fonts, and % 96.9, %98.84 for Arabic fonts, and% 98.21, %99.6 for English fonts. The most important advantages of our algorithm are low feature dimensions, lowcomputational complexity, and high speed compared with the previous efforts<\div>

۱۱A Fast Pipelined Lookup Table Based Hardware Implementation for Fractal Coding of Binary Images
نویسنده(ها): ، ،
اطلاعات انتشار: بیستمین کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۶
A pipelined hardware implementation is provided for a fast binary image fractal coding. The related algorithm suggests each range segment, R segment, is classified into threegroups of absolutely black, absolutely white, and nonmonochrome. For absolutely black and absolutely white R blocks, which are very probable in binary images, the requiredstorage and computation has low cost. For non–monochrome ones, number of white pixels in each R segment and the index ofcorresponding domain segment, D segment, for current R segment are stored. The low computational hamming distance isused for R and D segments comparison. Moreover, to speed up the fractal coding, a lookup table to retrieve coded range segment information are utilized. The encoder module is successfully synthesized to a FLEX10K family device. Experimental results show that the proposed algorithm is both fast and accurate.<\div>

۱۲A Hybrid Approach for Double Random Phase Encoding Technique Reinforcement
نویسنده(ها): ،
اطلاعات انتشار: بیستمین کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۶
this paper presents a new hybrid approach to increase security of double random phase encoding. Double random phase encoding (DRPE) disarranges the input image bythe use of two keys which are random phase masks. Having these keys, the original image can be easily obtained using thereverse process, called decoding. To heighten its security, instead of sending two phase masks, Initial conditions and parameter of chaotic map and SHA–512 algorithm aretransferred to the authorized user through a secure channel and the encoded image is embedded into a host image. Atdestination, two random phase masks are generated by Hash function and chaos theory.. Experimental results show that the proposed method not only has high security but is resists to commonplace attacks.<\div>

۱۳Double random phase encoding method usinginterleaving algorithm for security consideration
نویسنده(ها): ،
اطلاعات انتشار: هفتمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۵
This paper proposed a new watermarking methodbased on double random phase encoding (DRPE). In theconventional DRPE method, two random phase masks (keys) areneeded. Obviating the need of sending large keys through asecure channel, we generated the Fourier mask by interleavingprocess. Having the interleaver key and source image, thewatermark can be reconstructed. Experimental results show thatthe proposed method is robust to noise and attacks.<\div>

۱۴Fractal and Multi–Fractal DimensionsFor Farsi\Arabic Font Type and Size Recognition
اطلاعات انتشار: هفتمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۴
In this paper, a new method based on fractal geometryis proposed for Farsi\Arabic font recognition. The featureextraction does not depend on the document contents whichconsiders font recognition problem as texture identification task.The main features are obtained by combining the BCD, DCD,and DLA techniques. Dataset includes 2000 samples of 10typefaces, each containing four sizes. The average recognitionrates obtained for these 10 fonts and 4 sizes (40 classes) usingRBF and KNN classifiers are 96% and 91% respectively. Thedimension of feature vectors extracted by the proposed fractalapproach is very low. This property obviates the need fornumerous training samples. Experimental results show that thisalgorithm is robust against skew. Simultaneously identifying typeand size of the font is the most important innovation of thispaper.<\div>

۱۵Image Encryption Using Genetic Algorithm
نویسنده(ها): ،
اطلاعات انتشار: هشتمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۵
This paper presents a new method for imageencryption using Genetic algorithm (GA). First, rows andcolumns of the input image are dislocated randomly. Then, theobtained image is divided into four equal sized sub–images. Afterselecting one of these sub–images accidentally, two pixels arechosen from it as GA initial population. Cross–over andmutation operations are applied on the binary values of theselected pixels. Then the image is reconstructed in the reversemanner. If entropy of the result image increases, the current subimageis utilized for the next step. Otherwise, another sub–imagesis chosen randomly and the same process is applied. Randomnessof the encrypted image is measured by entropy, correlationcoefficients and histogram analysis. Experimental results showthat the proposed method can be used effectively for imageencryption.<\div>

۱۶Improving Security of Double Random Phase Encoding with Chaos Theory using Fractal Images
نویسنده(ها): ،
اطلاعات انتشار: International Journal of Information Security، چهارم،شماره۲، Jul ۲۰۱۲، سال
تعداد صفحات: ۱۰
This study presents a new method based on the combination of cryptography and information hiding methods. Firstly, the image is encoded by the Double Random Phase Encoding (DRPE) technique. The real and imaginary parts of the encoded image are subsequently embedded into an enlarged normalized host image. DRPE demands two random phase mask keys to decode the decrypted image at the destination. The two random phase masks are regenerated by the chaos theory using a fractal image. To enhance its security, instead of sending the second phase mask directly, the initial conditions and the parameter of the chaotic map and the fractal image are transferred to the authorized user through a secure channel. Experimental results reveal that the proposed method not only enjoys high security but also resists the commonplace attacks.

۱۷HWS: A Hierarchical Word Spotting Method for Farsi Printed Words Through Word Shape Coding
اطلاعات انتشار: International Journal Information and Communication Technology Research، هفتم،شماره۲، spring ۲۰۱۵، سال
تعداد صفحات: ۱۲
Word shape coding (WSC) is a method of document image retrieval (DIR) based on keyword spotting. By using this method, a word can be recognized in the document image, only by identifying some of the features of the word. In this paper, a hierarchical word spotting method, namely HWS, is presented for Farsi document image retrieval through WSC. In HWS method, document images are retrieved by using a new indexing method. In HWS, at first the words in the document images are shape coded based on topological properties. These features include number of sub–words, ascenders, descenders, and holes.A new feature that has been used for this paper is dot''s position in word. Six features are obtained which are one top dot, two top dots, three top dots and one bottom dot, two bottom dots, and three bottom dots. Precision of retrieval increases by using these features. Then, all of the shape codes are indexed by building a tree. Retrieval is done based on keyword query in the tree. The results show that the proposed technique is very fast for large volumes of documents. Time complexity for successful and non–successful searching is (log ) n kO .This value is better than values in ordinal method. Also, time complexity for indexing is (log ) n kO . The HWS method is tested on Bijankhan database. 87867 common words from this database are used for building the dictionary. Test results show that average of precision is 0.83 and average recall is 0.94.
نمایش نتایج ۱ تا ۱۷ از میان ۱۷ نتیجه