Adaptive local thresholding by verification-based multithreshold probing with application to vessel detection in retinal images

In this paper, we propose a general framework of adaptive local thresholding based on a verification-based multithreshold probing scheme. Object hypotheses are generated by binarization using hypothetic thresholds and accepted/rejected by a verification procedure. The application-dependent verification procedure can be designed to fully utilize all relevant informations about the objects of interest. In this sense, our approach is regarded as knowledge-guided adaptive thresholding, in contrast to most algorithms known from the literature. We apply our general framework to detect vessels in retinal images. An experimental evaluation demonstrates superior performance over global thresholding and a vessel detection method recently reported in the literature. Due to its simplicity and general nature, our novel approach is expected to be applicable to a variety of other applications.     

Multi-scale completed local binary patterns for ulcer detection in wireless capsule endoscopy images

Multimedia Tools and Applications - This paper deals with ulcer abnormalities detection of small bowel, from wireless capsule endoscopy images (WCE). We propose a multi-scale approach based on...     

Learning local binary patterns for gender classification on real-world face images

Gender recognition is one of fundamental face analysis tasks. Most of the existing studies have focused on face images acquired under controlled conditions. However, real-world applications require gender classification on real-life faces, which is much more challenging due to significant appearance variations in unconstrained scenarios. In this paper, we investigate gender recognition on real-life faces using the recently built database, the Labeled Faces in the Wild (LFW). Local Binary Patterns (LBP) is employed to describe faces, and Adaboost is used to select the discriminative LBP features. We obtain the performance of 94.81% by applying Support Vector Machine (SVM) with the boosted LBP features. The public database used in this study makes future benchmark and evaluation possible.     

Computer-aided retinal vessel segmentation in retinal images: convolutional neural networks

In medicine, diagnosis is as important as treatment. Retinal blood vessels are the most easily visible vessels in the whole body, and therefore, play a key role in the diagnosis of numerous diseases and eye disorders. Systematic and eye diseases cause morphologic variations, such as the growing, narrowing or branching of retinal blood vessels. Imaging-based screening of retinal blood vessels plays an important role in the identification and follow-up of eye diseases. Therefore, automatic retinal vessel segmentation can be used to diagnose and monitor those diseases. Computer-aided algorithms are required for the analysis of progression of eye diseases. This study proposes a hybrid method that provides a combination of pre-processing and data augmentation methods with a deep learning model. Pre-processing was used to solve the irregular clarification problems and to form a contrast between the background and retinal blood vessels. After pre-processing step, a convolutional neural network (CNN) was designed and then trained for the extraction of retinal blood vessels. In the training phase, data augmentation was performed to improve training performance. The CNN was trained and tested in the DRIVE database, which is commonly used in retinal blood vessel segmentation and publicly available for studies in this area. Results showed that the proposed system extracted vessels with a sensitivity of 77.78%, specificity of 97,84%, precision of 84.17% and accuracy of 95.27%.

This study also compared the results to those of previous studies. The comparison showed that the proposed method is an efficient and successful method for extracting retinal blood vessels. Moreover, the pre-processing phases improved the system performance. We believe that the proposed method and results will make contribution to the literature.

     

Aeroplane detection in very-high-resolution images using deep feature representation and rotation-invariant Hough forests

This letter proposes a processing chain for detecting aeroplanes from very high-resolution (VHR) remotely sensed images with the fusion of deep feature representation and rotation-invariant Hough forests. First, superpixel segmentation is used to generate meaningful and non-redundant patches. Second, deep learning techniques are exploited to construct a multi-layer feature encoder for representing high-order features of patches. Third, a set of multi-scale rotation-invariant Hough forests are trained to detect aeroplanes of varying orientations and sizes. Experiments show that the proposed method is a promising solution for detecting aeroplanes from VHR remotely sensed images, with a completeness, correctness, and F-measure of 0.956, 0.970, and 0.963, respectively. Comparative studies with four existing methods also demonstrate that the proposed method outperforms the other existing methods in accurately detecting aeroplanes of varying appearances, orientations, and sizes.     

Automatic detection and characterisation of retinal vessel tree bifurcations and crossovers in eye fundus images

Analysis of retinal vessel tree characteristics is an important task in medical diagnosis, specially in cases of diseases like vessel occlusion, hypertension or diabetes. The detection and classification of feature points in the arteriovenous eye tree will increase the information about the structure allowing its use for medical diagnosis. In this work a method for detection and classification of retinal vessel tree feature points is presented. The method applies and combines imaging techniques such as filters or morphologic operations to obtain an adequate structure for the detection. Classification is performed by analysing the feature points environment. Detection and classification of feature points is validated using the VARIA database. Experimental results are compared to previous approaches showing a much higher specificity in the characterisation of feature points while slightly increasing the sensitivity. These results provide a more reliable methodology for retinal structure analysis.     

Minimising retinal vessel artefacts in optical coherence tomography images

Optical coherence tomography (OCT) is commonly used to investigate the layers of the retina including retinal nerve fiber layer (RNFL) and retinal pigment epithelium (RPE). OCT images are altered by vessels on the retinal surface producing artefacts. We propose a new approach to compensate for these artefacts and enhance quality of OCT images. A total of 28 (20 normal and 8 glaucoma subjects) OCT images were obtained using Spectralis (Heidelberg, Germany). Shadows were detected along the image and compensated by the A-Scan intensity difference from surrounding non-affected areas. Images were then segmented and the area and thickness of RNFL and RPE were measured and compared. 10 subjects were tested twice to determine the effect of this on reproducibility of measurements. Shadow-suppressed images reflected the profile of the retinal layers more closely when assessed qualitatively, minimising distortion. The segmentation of RNFL and RPE thickness demonstrated a mean change of 2.4% ± 1 and 6% ± 1 from the original images. Much larger changes were observed in areas with vessels. Reproducibility of RNFL thickness was improved, specifically in the higher density vessel location, i.e. inferior and superior. Therefore, OCT images can be enhanced by an image processing procedure. Vessel artefacts may cause errors in assessment of RNFL thickness and are a source of variability, which has clinical implications for diseases such as glaucoma where subtle changes in RNFL need to be monitored accurately over time.     

Multiresolution approach for multiple human detection using moments and local binary patterns

Human detection is a central problem in development of any surveillance application. In this study, we present a simple and efficient, multi-resolution gray scale invariant approach for multiple human detection. The multiresolution is important for objects of different size and gray scale invariance is important due to uneven illumination and within-class variability. The proposed method is based on integration of central moments upon multi-resolution gray scale invariant local binary patterns operator. Since, the local binary patterns operator is invariant against different resolutions of space scale and monotonic change in gray scale, therefore the proposed method is robust in terms of variations in space scale as well as gray scale. Another advantage is high computational accuracy of the method due to use of moment operator which enhances the efficiency of the proposed method. Moreover, the proposed method is simple, as these operations can be performed within a few steps in a small neighborhood and a lookup table. The proposed method is tested on multiple human images and experimentally found appropriate for multiple human detection. The proposed method has been evaluated over two datasets, one is our own created dataset and the other is standard INRIA human detection dataset. Experimental results obtained from the proposed method demonstrate that better discrimination can be achieved for human and non-human objects in real scenes.     

A quantum mechanics-based algorithm for vessel segmentation in retinal images

Blood vessel segmentation is an important step in retinal image analysis. It is one of the steps required for computer-aided detection of ophthalmic diseases. In this paper, a novel quantum mechanics-based algorithm for retinal vessel segmentation is presented. The algorithm consists of three major steps. The first step is the preprocessing of the images to prepare the images for further processing. The second step is feature extraction where a set of four features is generated at each image pixel. These features are then combined using a nonlinear transformation for dimensionality reduction. The final step is applying a recently proposed quantum mechanics-based framework for image processing. In this step, pixels are mapped to quantum systems that are allowed to evolve from an initial state to a final state governed by Schrödinger’s equation. The evolution is controlled by the Hamiltonian operator which is a function of the extracted features at each pixel. A measurement step is consequently performed to determine whether the pixel belongs to vessel or non-vessel classes. Many functional forms of the Hamiltonian are proposed, and the best performing form was selected. The algorithm is tested on the publicly available DRIVE database. The average results for sensitivity, specificity, and accuracy are 80.29, 97.34, and 95.83 %, respectively. These results are compared to some recently published techniques showing the superior performance of the proposed method. Finally, the implementation of the algorithm on a quantum computer and the challenges facing this implementation are introduced.     

Multiresolution gray-scale and rotation invariant textureclassification with local binary patterns

Presents a theoretically very simple, yet efficient, multiresolution approach to gray-scale and rotation invariant texture classification based on local binary patterns and nonparametric discrimination of sample and prototype distributions. The method is based on recognizing that certain local binary patterns, termed "uniform," are fundamental properties of local image texture and their occurrence histogram is proven to be a very powerful texture feature. We derive a generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis. The proposed approach is very robust in terms of gray-scale variations since the operator is, by definition, invariant against any monotonic transformation of the gray scale. Another advantage is computational simplicity as the operator can be realized with a few operations in a small neighborhood and a lookup table. Experimental results demonstrate that good discrimination can be achieved with the occurrence statistics of simple rotation invariant local binary patterns