Vaclav Uher

Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus image

Glaucoma is a disease of the retina which is one of the most common causes of permanent blindness worldwide. This paper presents an automatic image processing based method for glaucoma diagnosis from the digital fundus image. In this paper wavelet feature extraction has been followed by optimized genetic feature selection combined with several learning algorithms and various parameter settings. Unlike the existing research works where the features are considered from the complete fundus or a sub image of the fundus, this work is based on feature extraction from the segmented and blood vessel removed optic disc to improve the accuracy of identification. The experimental results presented in this paper indicate that the wavelet features of the segmented optic disc image are clinically more significant in comparison to features of the whole or sub fundus image in the detection of glaucoma from fundus image. Accuracy of glaucoma identification achieved in this work is 94.7% and a comparison with existing methods of glaucoma detection from fundus image indicates that the proposed approach has improved accuracy of classification.

Evolutionary improved object detector for ultrasound images

Object detection in ultrasound images is difficult problem mainly because of relatively low signal-to-noise ratio. This paper deals with object detection in the noisy ultrasound images using modified version of Viola-Jones object detector. The method describes detection of carotid artery longitudinal section in ultrasound B-mode images. The detector is primarily trained by AdaBoost algorithm and uses a cascade of Haar-like features as a classifier. The main contribution of this paper is a method for detection of carotid artery longitudinal section. This method creates cascade of classifiers automatically using genetic algorithms. We also created post-processing method that marks position of artery in the image. The proposed method was released as open-source software. Resulting detector achieved accuracy 96.29%. When compared to SVM classification enlarged with RANSAC (RANdom SAmple Consensus) method that was used for detection of carotid artery longitudinal section, works our method real-time.

Automatic 3D segmentation of human brain images using data-mining techniques

This paper proposes a method for automatic 3D segmentation of human brain CT scans using data mining techniques. The brain scans are processed in 2D and 3D. The proposed method has several steps - image pre-processing, segmentation, feature extraction from segments, data mining, and post-processing. The method introduced is implemented in 3D image processing extension for the RapidMiner platform, and both are provided as open source. With testing data the resultant performance selection of tissue slices from the brain image was 98.08% when compared to human expert results.

3D brain tissue selection and segmentation from MRI

Magnetic resonance imaging (MRI) is a visualizing method used in radiology that enables viewing internal structures of the body. Using several mathematical methods with data retrieved from MRI it is possible to quantify the brain compartment volume, which has many applications in cognitive, clinical and comparative neurosciences. This paper introduces a new fully automatic method, which can measure the volume of brain tissue using scans obtained from MRI devices. The method introduced in this paper was trained on data taken from 12 patients and the trained result was validated on other independent data obtained from 10 patients and compared to a human experts accuracy. The result achieves 99.407 % +/- 0.062 voxel error accuracy, which is comparable to results achieved by humans (99.540 % + 0.0775) but in a significantly shorter time and without the need of human involvement.

Speeding up Viola-Jones algorithm using multi-Core GPU implementation

Graphic Processing Units (GPUs) offer cheap and high-performance computation capabilities by offloading compute-intensive portions of the application to the GPU, while the remainder of the code still runs on a CPU. This paper introduces an multi-GPU CUDA implementation of training of object detection using Viola-Jones algorithm that has accelerated of two the most time consuming operations in training process by using two dual-core NVIDIA GeForce GTX 690. When compared to single thread implementation on Intel Core i7 3770 with 3.7 GHz frequency, the first accelerated part of training process was speeded up 151 times and the second accelerated part was speeded up 124 times using two dual-core GPUs. This paper examines overall computational time of the Viola-Jones training process with the use of: one core CPU, one GPU, two GPUs, 3 GPUs and 4GPUs. Trained detector was applied on testing set containing real world images.

Supervised video scene segmentation using similarity measures

Video scene segmentation is a process for dividing video into semantically meaningful blocks. This can help e.g. search engines to divide video into better manageable parts and enable more relevant search in video. Unfortunately, scene segmentation is based on the semantic and therefore it is a difficult task for computers. This work is preliminary study involved into supervised video scene segmentation, which is driven by the way how human segments scenes in a movie. Since these video segments represent semantic parts in video, it can be used for better video annotation and also for searching in videos. As a training set, only high quality movies were used and from these movies 100 training samples have been extracted and used for evaluation. Resulting model is a method based on general color layout, Tamura similarity measure and k-nearest neighbors achieving 97.00% accuracy.

Color image (dis)similarity assessment and grouping based on dominant colors

The computer vision connected to image understanding becomes more and more important in everyday life. This paper concerns the image (dis)similarity assessment and grouping. The main contribution of this paper is the method for image (dis)similarity assessment based on dominant colors. The experimental results showed better results than the Direct Pixel Similarity and Color Histograms and method proved to be capable of detecting images similar to the target image.

Edge based block wise selective fingerprint image encryption using chaos

Security and privacy of biometric data plays major concern due to extensive use of biometric systems in high security applications like access to confidential data, information security and financial access etc. This paper proposes an efficient and lossless method for securing fingerprint images using edge based block wise selective encryption based on chaotic theory. In this proposed technique, fingerprint image is segmented into significant and non significant blocks and encryption is applied upon significant blocks which reduces the computational overhead and processing time as compared to full encryption techniques. Experimental results shows that edge based block wise selective encryption significantly reduces the time of encryption of fingerprint images as compared to full encryption method without any compromise in performance which suits real time applications. Experimental results also indicate that upon decryption data is completely recovered making the proposed scheme lossless in nature which suits the requirements of biometric pattern recognition.

Automated Brain Tumor segmentation using novel feature point detector and seeded region growing

In this paper, we propose a methodology for fully automated Brain Tumor segmentation from T1 weighted contrast enhanced Magnetic Resonance Images. A novel algorithm has been designed to extract the visually significant feature points. Feature points relating to Tumor are then identified and extracted as seeds for further region growing. Feature points are obtained by fusion of wavelet methods and image edge maps. Robustness of feature points to geometrical transformations and scaling have been shown. Our method gives a sparse representation of the information (region of interest) in the medical image and thereby vastly improves upon the computational speed for tumor segmentation results.

Optimization of logistic distribution centers process planning and scheduling

This paper describes a novel method for solving the problem of automatic planning and scheduling of work-plans in logistic distribution centers. The solution of the problem is based on well-known scheduling problems such as Job-Shop Scheduling Problems or Vehicle Routing Problems. By the time of writing this article, the key representatives of the logistics and warehousing industry do not use fully automated processes for work scheduling. The purpose of this paper is to connect the scientific result with demands of the companies in logistics and warehousing industry. The main contribution of this paper is a) to describe the motivation for solving the problem of logistic and warehousing companies, b) to describe a set of benchmarks and to give the reference layout of the warehouse, and c) to present a baseline results obtained by a genetic programming.