Search published articles
Showing 8 results for Image Processing
Foruzan Fasahat, Pedram Payvandy,
Volume 12, Issue 4 (3-2016)
Volume 12, Issue 4 (3-2016)
Abstract
Flexibility of woven fabric structure has caused many errors in yarn location detection using customary methods of image processing. On this line, proposing an adaptive method with fabric image properties is concentrated to extract its parameters. In this regards, using meta-heuristic algorithms seems applicable to correspond extraction algorithm of structural parameters to the image conditions. In this study, a new method is proposed for woven fabric image preprocessing and structural texture detection applying compound methods of signal processing, fuzzy clustering and genetic algorithm. Results indicate that proposed method is capable of detecting exact yarn location with mean precision of more than 73 percent in double-layered fabric images with uneven color pattern. In one-layered fabric images with low density weave and invariable color pattern, the mean precision is more than 84 percent.
Engineer Faeze Karimi Zarchi, Doctor Vali Derhami, Doctor Alimohammad Latif, Engineer Ali Ebrahimi,
Volume 16, Issue 3 (12-2019)
Volume 16, Issue 3 (12-2019)
Abstract
Nowadays automated early warning systems are essential in human life. One of these systems is fire detection which plays an important role in surveillance and security systems because the fire can spread quickly and cause great damage to an area. Traditional fire detection methods usually are based on smoke and temperature detectors (sensors). These methods cannot work properly in large space and out-door environments. They have high false alarm rates, and to cover the entire area, many smoke or temperature fire detectors are required, that is expensive. Due to the rapid developments in CCTV (Closed Circuit Television) surveillance system in recent years and video processing techniques, there is a big trend to replace conventional fire detection techniques with computer vision-based systems. This new technology can provide more reliable information and can be more cost-effective. The main objective of fire detection systems is high detection accuracy, low error rate and reasonable time detect. The video fire detection technology uses CCD cameras to capture images of the observed scene, which provides abundant and intuitive information for fire detection using image processing algorithms.
This paper presents an efficient fire detection system which detects fire areas by analyzing the videos that are acquired by surveillance cameras in urban out-door environment, especially in storage of Yazd Gas Company.
Proposed method uses color, spatial and temporal information that makes a good distinction between the fire and objects which are similar to the fire. The purpose is achieved using multi- filter. The first filter separates red color area as a primary fire candidate. The second filter operates based on the difference between fire candidate areas in the sequence of frames. In the last filter, variation of red channel in the candidate area is computed and compared with the threshold which is updating continuously. In the experiments, the performance of these filters are evaluated separately. The proposed final system is a combination of all filters. Experimental results show that the precision of the final proposed system in urban out-door environment is 100%, and our technique achieves the average detection rate of 87.35% which outperforms other base methods.
Mozhdeh Zandifar, Jafar Tahmoresnezhad,
Volume 16, Issue 3 (12-2019)
Volume 16, Issue 3 (12-2019)
Abstract
Image processing is a method to perform some operations on an image, in order to get an enhanced image or to extract some useful information from it. The conventional image processing algorithms cannot perform well in scenarios where the training images (source domain) that are used to learn the model have a different distribution with test images (target domain). Also, many real world applications suffer from a limited number of training labeled data and therefore benefit from the related available labeled datasets to train the model. In this way, since there is the distribution difference across the source and target domains (domain shift problem), the learned classifier on the training set might perform poorly on the test set. Transfer learning and domain adaptation are two outstanding solutions to tackle this challenge by employing available datasets, even with significant difference in distribution and properties, to transfer the knowledge from a related domain to the target domain. The main assumption in domain shift problem is that the marginal or the conditional distribution of the source and the target data is different. Distribution adaptation explicitly minimizes predefined distance measures to reduce the difference in the marginal distribution, conditional distribution, or both. In this paper, we address a challenging scenario in which the source and target domains are different in marginal distributions, and the target images have no labeled data. Most prior works have explored two following learning strategies independently for adapting domains: feature matching and instance reweighting. In the instance reweighting approach, samples in the source data are weighted individually so that the distribution of the weighted source data is aligned to that of the target data. Then, a classifier is trained on the weighted source data. This approach can effectively eliminate unrelated source samples to the target data, but it would reduce the number of samples in adapted source data, which results in an increase in generalization errors of the trained classifier. Conversely, the feature-transform approach creates a feature map such that distributions of both datasets are aligned while both datasets are well distributed in the transformed feature space. In this paper, we show that both strategies are important and inevitable when the domain difference is substantially large. Our proposed using sample-oriented Domain Adaptation for Image Classification (DAIC) aims to reduce the domain difference by jointly matching the features and reweighting the instances across images in a principled dimensionality reduction procedure, and construct new feature representation that is invariant to both the distribution difference and the irrelevant instances. We extend the nonlinear Bregman divergence to measure the difference in marginal, and integrate it with Fisher’s linear discriminant analysis (FLDA) to construct feature representation that is effective and robust for substantial distribution difference. DAIC benefits pseudo labels of target data in an iterative manner to converge the model. We consider three types of cross-domain image classification data, which are widely used to evaluate the visual domain adaptation algorithms: object (Office+Caltech- 256), face (PIE) and digit (USPS, MNIST). We use all three datasets prepared by and construct 34 cross-domain problems. The Office-Caltech-256 dataset is a benchmark dataset for cross-domain object recognition tasks, which contains 10 overlapping categories from following four domains: Amazon (A), Webcam (W), DSLR (D) and Caltech256 (C). Therefore 4 × 3 = 12 cross domain adaptation tasks are constructed, namely A → W, ..., C → D. USPS (U) and MNIST (M) datasets are widely used in computer vision and pattern recognition tasks. We conduct two handwriting recognition tasks, i.e., usps-mnist and mnist-usps. PIE is a benchmark dataset for face detection task and has 41,368 face images of size 3232 from 68 individuals. The images were taken by 13 synchronized cameras and 21 flashes, under varying poses, illuminations, and expressions. PIE dataset consists five subsets depending on the different poses as follows: PIE1 (C05, left pose), PIE2 (C07, upward pose), PIE3 (C09, downward pose), PIE4 (C27, frontal pose), PIE5 (C29, right pose). Thus, we can construct 20 cross domain problems, i.e., P1 → P2, P1 → P3, ..., P5 → P4. We compare our proposed DAIC with two baseline machine learning methods, i.e., NN, Fisher linear discriminant analysis (FLDA) and nine state-of-the-art domain adaptation methods for image classification problems (TSL, DAM, TJM, FIDOS and LRSR). Due to these methods are considered as dimensionality reduction approaches, we train a classifier on the labeled training data (e.g., NN classifier), and then apply it on test data to predict the labels of the unlabeled target data. DAIC efficiently preserves and utilizes the specific information among the samples from different domains. The obtained results indicate that DAIC outperforms several state of-the-art adaptation methods even if the distribution difference is substantially large.
Reza Mozaffari, Samira Mavaddati,
Volume 16, Issue 4 (3-2020)
Volume 16, Issue 4 (3-2020)
Abstract
In this paper, a new method for image denoising based on incoherent dictionary learning and domain transfer technique is proposed. The idea of using sparse representation concept is one of the most interesting areas for researchers. The goal of sparse coding is to approximately model the input data as a weighted linear combination of a small number of basis vectors. Two characteristics should be considered in the dictionary learning process: Atom-data coherence and mutual coherence between dictionary atoms. The first one determines the dependency between the dictionary atoms and training data frames. This criterion value should be high. Another parameter expresses the dependency between atoms defined as the maximum absolute value of the cross-correlations between them. Higher coherence to the data class and lower mutual coherence between atoms result in a small approximation error in sparse coding procedure. In the proposed dictionary learning process, a coherence criterion is employed to yield over complete dictionaries with the incoherent atoms. The purpose of learning dictionary with low mutual coherence value is to reduce the approximation error of sparse representation in the denoising process and also decrease the computing time.
We utilize the least angle regression with coherence criterion (LARC) algorithm for sparse representation based on atom-data coherence in the first step of dictionary learning process. LARC sparse coding is an optimized generalization of the least angle regression algorithm with stopping condition based on a residual coherence. This approach is based on setting a variable cardinality value.
Using atom-data coherence measure as stopping criteria in the sparse coding process yields the capability of balancing between source confusion and source distortion. A high value for the cardinality parameter or too dense coding results in the source confusion since the number of dictionary atoms is more than what is required for a proper representation. Source degradation occurs when the sparse coding is done with low cardinality parameter or too sparse coding. Therefore, the number of required atoms will not be enough and data cannot be coded exactly over these atoms. Therefore, the setting procedure of cardinality parameter must be performed precisely.
The problem of finding a dictionary with low mutual coherence between its normalized atoms can be obtained by considering the Gram matrix. The mutual coherence is described by the maximum absolute value of the off-diagonal elements of this matrix. If all off-diagonal elements are the same, a dictionary with minimum self-coherence value is obtained.
Also, we take advantage of domain adaptation technique to transfer a learned dictionary to an adapted dictionary in the denoising process. The initial atoms set randomly and are updated based on the selected patches of input noisy image using the proposed alternating optimization algorithm.
According to these issues, the fitness function in dictionary learning problem includes three main sections: The first term is related to the minimization of approximation error. The next items are the incoherence criterion of dictionary atoms. The last one includes a transformation of initial atoms according to some patches of the noisy input data in the test step. We use limited-memory BFGS algorithm as an iterative solution for regular minimization of our objective function involved different terms. The simulation results show that the proposed method leads to significantly better results in comparison with the earlier methods in this context and the traditional procedures.
We utilize the least angle regression with coherence criterion (LARC) algorithm for sparse representation based on atom-data coherence in the first step of dictionary learning process. LARC sparse coding is an optimized generalization of the least angle regression algorithm with stopping condition based on a residual coherence. This approach is based on setting a variable cardinality value.
Using atom-data coherence measure as stopping criteria in the sparse coding process yields the capability of balancing between source confusion and source distortion. A high value for the cardinality parameter or too dense coding results in the source confusion since the number of dictionary atoms is more than what is required for a proper representation. Source degradation occurs when the sparse coding is done with low cardinality parameter or too sparse coding. Therefore, the number of required atoms will not be enough and data cannot be coded exactly over these atoms. Therefore, the setting procedure of cardinality parameter must be performed precisely.
The problem of finding a dictionary with low mutual coherence between its normalized atoms can be obtained by considering the Gram matrix. The mutual coherence is described by the maximum absolute value of the off-diagonal elements of this matrix. If all off-diagonal elements are the same, a dictionary with minimum self-coherence value is obtained.
Also, we take advantage of domain adaptation technique to transfer a learned dictionary to an adapted dictionary in the denoising process. The initial atoms set randomly and are updated based on the selected patches of input noisy image using the proposed alternating optimization algorithm.
According to these issues, the fitness function in dictionary learning problem includes three main sections: The first term is related to the minimization of approximation error. The next items are the incoherence criterion of dictionary atoms. The last one includes a transformation of initial atoms according to some patches of the noisy input data in the test step. We use limited-memory BFGS algorithm as an iterative solution for regular minimization of our objective function involved different terms. The simulation results show that the proposed method leads to significantly better results in comparison with the earlier methods in this context and the traditional procedures.
Ms Narjes Hajizadeh, Dr Hamed Vahdat-Nejad, Dr Ramazan Havangi,
Volume 20, Issue 3 (12-2023)
Volume 20, Issue 3 (12-2023)
Abstract
Subject- Today, with the advancement of technologies to assist blind and visually impaired people, navigation systems are of great importance. As a result of emerging technologies in telecommunication and smartphones, these people can be helped. Identifying pedestrian and traffic lights is important to help pedestrians with visual impairments cross the intersection safely and securely.
Background- researchers have studied the detection and identification of traffic lights in the assistive system or blind assist device. These researches can be divided into three main types: based on pattern matching, based on circular shape extraction, and based on color distribution.
Methodology- In this research, an architecture based on mobile cloud computing is proposed, which can help blind pedestrians in crossing intersections. The architecture consists of three tiers: mobile phone, cloud, and supervision. The most important component is located on the mobile phone. It recognizes the color of pedestrian light by using image processing techniques. Spatial information (time and location) of the blind person is collected and held in a cloud storage database so that acquaintances can monitor him if needed. In order to detect the status of pedestrian lights, pictures of crossing streets with cameras will be captured. Using the features of color and morphology operations, the color of pedestrian lights is recognized and reported to the blind person. To this end, morphological operations are performed to eliminate small elements in the background and to restore the original size of the traffic light sign. Therefore, the operations of dilation, filling, and erosion are used.
Result- We gathered a dataset including 280 photos of pedestrian lights (170 photos at day, 110 photos at night) in different illumination conditions (early day, noon, early night, night) and weather (sunny, cloudy, rainy). Matlab software and notebook system with Intel (R) Core (TM) i5 CPU and AMD Mobility Radeon HD 5100 graphics card were used to implement pedestrian traffic-light status detection. The scenario-based method is used to evaluate the system architecture and show that the proposed system can satisfy the investigated scenario. At last, the implementation results on taken images show excellent performance in detecting pedestrian lights with approximately 100% accuracy for the day and night.
Mahdi Ahmadnia, Mojtaba Maghrebi, Reza Ghanbari,
Volume 21, Issue 2 (10-2024)
Volume 21, Issue 2 (10-2024)
Abstract
Low-light images often suffer from low brightness and contrast, which makes some scene details hard to see. This can affect the performance of many computer vision tasks, such as object recognition, tracking, scene understanding, and occlusion detection. Therefore, it is important and useful to enhance low-light images. One technique to enhance low-light images is based on the Retinex theory, which decomposes images into two components: reflection and illumination. Several mathematical models have been recently developed to estimate the illumination map using this theory. These methods first compute an initial illumination map and then refine it by solving a mathematical model.
This paper introduces a novel method based on the Retinex theory to estimate the illumination map. The proposed method employs a new mathematical model with a differentiable objective function, unlike other similar models. This allows us to use more diverse methods to solve the proposed model, as classical optimization methods such as Newton, Gradient, and Trust-Region methods need the objective function to be differentiable. The proposed model also has linear constraints and is convex, which are desirable properties for optimization. We use the CPLEX solver to solve the proposed model, as it performs well and exploits the features of the model. Finally, we improve the illumination map obtained from the mathematical model using a simple linear transformation.
This paper introduces a new method based on the Retinex theory for enhancing low-light images. The proposed method improves the illumination and the visibility of the scene details. We compare the performance of our method with six existing methods: AMSR, NPE, SRIE, DONG, MF, and LIME. We use four common metrics to evaluate the visual quality of the enhanced images: AMBE, LOE, SSIM, and NIQE. The results demonstrate that our method is competitive with many of the state-of-the-art methods for low-light image enhancement.
This paper introduces a novel method based on the Retinex theory to estimate the illumination map. The proposed method employs a new mathematical model with a differentiable objective function, unlike other similar models. This allows us to use more diverse methods to solve the proposed model, as classical optimization methods such as Newton, Gradient, and Trust-Region methods need the objective function to be differentiable. The proposed model also has linear constraints and is convex, which are desirable properties for optimization. We use the CPLEX solver to solve the proposed model, as it performs well and exploits the features of the model. Finally, we improve the illumination map obtained from the mathematical model using a simple linear transformation.
This paper introduces a new method based on the Retinex theory for enhancing low-light images. The proposed method improves the illumination and the visibility of the scene details. We compare the performance of our method with six existing methods: AMSR, NPE, SRIE, DONG, MF, and LIME. We use four common metrics to evaluate the visual quality of the enhanced images: AMBE, LOE, SSIM, and NIQE. The results demonstrate that our method is competitive with many of the state-of-the-art methods for low-light image enhancement.
Mr. Daniyal Haghparast, Dr. Ali Mohammad Fotouhi,
Volume 21, Issue 4 (3-2025)
Volume 21, Issue 4 (3-2025)
Abstract
One of the important factors in traffic accidents is the fatigue and drowsiness of the driver. In this paper, by using the driver's face detection and eye state recognition based on image processing and artificial intelligence, the driver's drowsiness is detected, and appropriate alarms sound to wake up the driver. The proposed method is implemented on the driver's mobile phone and uses the facilities of the phone, including processor, camera, and alarm, so it requires no additional hardware in the car. The method used and implemented in order to detect and determine the position of the face is based on the Hare-Cascade algorithm. In order to further speed up the algorithm by combining the two stages of eye detection and eye state detection, the Hare-Cascade method has been used to detect open eyes in the face area. The proposed algorithm, while providing the necessary accuracy, unlike the existing numerous and advanced algorithms, including algorithms based on deep learning, has a low computational cost and can be implemented in real time on different types of smart mobile phones. Also, by adjusting the sensitivity of the software by the user, based on the detection of one or two open eyes in the area of the face and the time between two consecutive frames of not detecting open eyes, increasing the number of correct alarms and reducing the number of false alarms can be controlled.
In this research to train and increase the accuracy of the intelligent model used, a database of 500 suitable images in different driving situations was prepared and used. Experimental results on 20 test videos in different driving situations show the proper performance of the designed system by creating 95% of the expected alarms. Based on the results of numerous and various experimental tests with the acceptable performance of the product of this applied research in detecting driver drowsiness and creating correct alarms, it seems that if used by drivers, it can prevent many car accidents.
In this research to train and increase the accuracy of the intelligent model used, a database of 500 suitable images in different driving situations was prepared and used. Experimental results on 20 test videos in different driving situations show the proper performance of the designed system by creating 95% of the expected alarms. Based on the results of numerous and various experimental tests with the acceptable performance of the product of this applied research in detecting driver drowsiness and creating correct alarms, it seems that if used by drivers, it can prevent many car accidents.
| Page 1 from 1 |
Related Websites
Site Keywords
Vote
© 2015 All Rights Reserved | Signal and Data Processing