ASOD: Arbitrary shape object detection

Arbitrary shape object detection, which is mostly related to computer vision and image processing, deals with detecting objects from an image. In this paper, we consider the problem of detecting arbitrary shape objects as a clustering application by decomposing images into representative data points, and then performing clustering on these points. Our method for arbitrary shape object detection is based on COMUSA which is an efficient algorithm for combining multiple clusterings. Extensive experimental evaluations on real and synthetically generated data sets demonstrate that our method is very accurate and efficient.     

A robust object category detection system using deformable shapes

An object can often be uniquely identified by its shape, which is usually fairly invariant. However, when the search is for a type of object or an object category, there can be variations in object deformation (i.e. variations in body shapes) and articulation (i.e. joint movement by limbs) that complicate their detection. We present a system that can account for this articulation variation to improve the robustness of its object detection by using deformable shapes as its main search criteria. However, existing search techniques based on deformable shapes suffer from slow search times and poor best matches when images are cluttered and the search is not initialised. To overcome these drawbacks, our object detection system uses flexible shape templates that are augmented by salient object features and user-defined heuristics. Our approach reduces computation time by prioritising the search around these salient features and uses the template heuristics to find truer positive matches.

Face recognition using a fuzzy fisherface classifier

In this study, we are concerned with face recognition using fuzzy fisherface approach and its fuzzy set based augmentation. The well-known fisherface method is relatively insensitive to substantial variations in light direction, face pose, and facial expression. This is accomplished by using both principal component analysis and Fisher's linear discriminant analysis. What makes most of the methods of face recognition (including the fisherface approach) similar is an assumption about the same level of typicality (relevance) of each face to the corresponding class (category). We propose to incorporate a gradual level of assignment to class being regarded as a membership grade with anticipation that such discrimination helps improve classification results. More specifically, when operating on feature vectors resulting from the PCA transformation we complete a Fuzzy K-nearest neighbor class assignment that produces the corresponding degrees of class membership. The comprehensive experiments completed on ORL, Yale, and CNU (Chungbuk National University) face databases show improved classification rates and reduced sensitivity to variations between face images caused by changes in illumination and viewing directions. The performance is compared vis-à-vis other commonly used methods, such as eigenface and fisherface.     

Incorporating shape prior into geodesic active contours for detecting partially occluded object

A new method to incorporate shape prior knowledge into geodesic active contours for detecting partially occluded object is proposed in this paper. The level set functions of the collected shapes are used as training data. They are projected onto a low dimensional subspace using PCA and their distribution is approximated by a Gaussian function. A shape prior model is constructed and is incorporated into the geodesic active contour formulation to constrain the contour evolution process. To balance the strength between the image gradient force and the shape prior force, a weighting factor is introduced to adaptively guide the evolving curve to move under both forces. The curve converges with due consideration of both local shape variations and global shape consistency. Experimental results demonstrate that the proposed method makes object detection robust against partial occlusions.     

Face localization using fuzzy classifier with wavelet-localized focus color features and shape features

This paper proposes a new fuzzy classifier (FC)-based face localization approach. The FC used is a self-organizing TS-type fuzzy network with support vector learning (SOTFN-SV). The SOTFN-SV learns consequent parameters using a linear support vector machine to improve generalization ability. The FC is first applied to segment human skin pixels in scaled hue and saturation (hS) color space, after which connected skin-color regions are regarded as face candidates. The FC is then applied to detect and localize faces from the candidates. The proposed FC-based face localization approach uses shape and wavelet-localized focus color features. A best fitting ellipse of each face candidate is found to obtain shape features. Focus color features are extracted from four focus regions, including the two eyes, the mouth, and the face skin-color region. To find these focus color regions, the Haar-wavelet transformation is first applied to the face candidates in the YCb color space to localize all possible pairs of eye candidates. The mouth region is then localized according to its geometric relationship with the eyes. The hS color features of the located eyes, mouth, and face skin are extracted. These focus color features, together with shape features, serve as inputs to another FC for final face localization. Comparisons with various classifiers and face detection methods demonstrate the advantage of the FC-based skin color segmentation and face localization method.     

Object detection,shape recovery,and 3D modelling by depth-encoded hough voting

Detecting objects, estimating their pose, and recovering their 3D shape are critical problems in many vision and robotics applications. This paper addresses the above needs using a two stages approach. In the first stage, we propose a new method called DEHV – Depth-Encoded Hough Voting. DEHV jointly detects objects, infers their categories, estimates their pose, and infers/decodes objects depth maps from either a single image (when no depth maps are available in testing) or a single image augmented with depth map (when this is available in testing). Inspired by the Hough voting scheme introduced in [1], DEHV incorporates depth information into the process of learning distributions of image features (patches) representing an object category. DEHV takes advantage of the interplay between the scale of each object patch in the image and its distance (depth) from the corresponding physical patch attached to the 3D object. Once the depth map is given, a full reconstruction is achieved in a second (3D modelling) stage, where modified or state-of-the-art 3D shape and texture completion techniques are used to recover the complete 3D model. Extensive quantitative and qualitative experimental analysis on existing datasets [2], [3], [4] and a newly proposed 3D table-top object category dataset shows that our DEHV scheme obtains competitive detection and pose estimation results. Finally, the quality of 3D modelling in terms of both shape completion and texture completion is evaluated on a 3D modelling dataset containing both in-door and out-door object categories. We demonstrate that our overall algorithm can obtain convincing 3D shape reconstruction from just one single uncalibrated image.     

Rules discovery in fuzzy classifier systems with PSO for scheduling in grid computational infrastructures

Particle swarm optimization (PSO) is a bio-inspired optimization strategy founded on the movement of particles within swarms. PSO can be encoded in a few lines in most programming languages, it uses only elementary mathematical operations, and it is not costly as regards memory demand and running time. This paper discusses the application of PSO to rules discovery in fuzzy classifier systems (FCSs) instead of the classical genetic approach and it proposes a new strategy, Knowledge Acquisition with Rules as Particles (KARP). In KARP approach every rule is encoded as a particle that moves in the space in order to cooperate in obtaining high quality rule bases and in this way, improving the knowledge and performance of the FCS. The proposed swarm-based strategy is evaluated in a well-known problem of practical importance nowadays where the integration of fuzzy systems is increasingly emerging due to the inherent uncertainty and dynamism of the environment: scheduling in grid distributed computational infrastructures. Simulation results are compared to those of classical genetic learning for fuzzy classifier systems and the greater accuracy and convergence speed of classifier discovery systems using KARP is shown.     

Two-dimensional shape decomposition using fuzzy subset theory applied to automated chromosome analysis

This paper describes a technique to transform a two-dimensional shape into a generalized fuzzy binary relation whose clusters represent the meaningful simple parts of the shape. The fuzzy binary relation is defined on the set of convex and concave boundary points, implying a piecewise linear approximation of the boundary, and describes the dissemblance of two vertices to a common cluster. Next some fuzzy subsets are defined over the points which determine the connection between the clusters.The decomposition method first determines nearly convex regions, which are subgraphs of the total graph, and then selects the greatest nearly convex region which satisfies best the defined fuzzy subsets and relations. Using this procedure on touching chromosomes defining the simple parts to be the separated chromosomes, the decomposition often corresponds well to the decomposition that a human might make.     

Visitor-artwork network analysis using object detection with image-retrieval technique

Recent museum exhibitions are becoming a means by which to satisfy visitor demands. In order to provide visitor-centric exhibitions, artwork must be analyzed based on the behavior of visitors, and not merely according to museum professionals' points of view. This study aims to analyze the relationship between museum visitors and artwork via a network analysis based on visitor behavior using object detection techniques. Cameras installed in a museum recorded visitors, and an object detector with a content-based image-retrieval technique tracked visitors from the videos. The durations spent with different artworks were measured, and the data was converted into a bipartite graph. The relationships between different artwork types were analyzed with a visitor-centered artwork network. Based on the visitors’ behavior, significant artworks were identified and the artwork network was compared to the arrangement of the museum. The tendency of edges in the artwork network was also examined considering visitors' preferences for artworks. The method used here makes it possible to collect quantitative data, with the results possibly used as a basis and for reference when analyzing artwork in a visitor-centered approach.     

A new algorithm for ball recognition using circle Hough transform and neural classifier

A large number of methods for circle detection have been studied in the last years for several image processing applications. The context application considered in this work is the soccer game. In the sequences of soccer images it is very important to identify the ball in order to verify the goal event. This domain is a challenging one as a great number of problems have to be faced, such as occlusions, shadows, objects similar to the ball, real-time processing and so on. In this work a visual framework trying to solve the above-stated problems, mainly considering real-time computational aspects, has been developed. The ball detection algorithm has to be very simple in terms of time processing and also has to be efficient in terms of false positive rate. Our framework consists of two sequential steps for solving the ball recognition problem: the first step uses a modified version of the directional circle Hough transform to detect the region of the image that is the best candidate to contain the ball; in the second step a neural classifier is applied on the selected region to confirm if the ball has been properly detected or a false positive has been found. Some tricks like background subtraction and ball tracking have been applied in order to maintain the search of the ball only in limited areas of the image. Different light conditions have been considered as they introduce strong modifications on the appearance of the ball in the image: when the image sequences are taken with natural light, as the light source is strictly directional, the ball, due to self-shades, appears as a spherical cap; this case has been taken in account and the search of the ball has been modified in order to manage this situation. A large number of experiments have been carried out showing that the proposed method obtains a high detection score.     

Motion detection and object tracking with discrete leaky integrate-and-fire neurons

A biologically inspired visual system capable of motion detection and pursuit motion is implemented using a Discrete Leaky Integrate-and-Fire (DLIF) neuron model. The system consists of a visual world, a virtual retina, the neural network circuitry (DLIF) to process the information, and a set of virtual eye muscles that serve to move the input area (visual field) of the retina within the visual world. Temporal aspects of the DLIF model are heavily exploited including: spike propagation latency, relative spike timing, and leaky potential integration. A novel technique for motion detection is employed utilizing coincidence detection aspects of the DLIF and relative spike timing. The system as a whole encodes information using relative spike timing of individual action potentials as well as rate coded spike trains. Experimental results are presented in which the motion of objects is detected and tracked in real and animated video. Pursuit motion is successful using linear and also sinusoidal paths which include object velocity changes. The visual system exhibits dynamic overshoot correction heavily exploiting neural network characteristics. System performance is within the bounds of real-time applications.     

Classification based on fuzzy robust PCA algorithms and similarity classifier

In this article, classification method is proposed where data is first preprocessed using fuzzy robust principal component analysis (FRPCA) algorithms to obtain data in a more feasible form. After this we use similarity classifier for the classification. We tested this procedure for breast cancer data and liver-disorder data. The results were quite promising and better classification accuracy was achieved than using traditional PCA and similarity classifier. Fuzzy robust principal component analysis algorithms seem to have the effect that they project these data sets in a more feasible form, and together with similarity classifier classification on accuracy of 70.25% was achieved with liver-disorder data and 98.19% accuracy was achieved with breast cancer data. Compared to the results achieved with traditional PCA and similarity classifier about 4% higher accuracy was achieved with liver-disorder data and about 0.5% higher accuracy was achieved with breast cancer data.     

Fuzzy-neural self-adapting background modeling with automatic motion analysis for dynamic object detection

In this paper we propose a system that involves a Background Subtraction, BS, model implemented in a neural Self Organized Map with a Fuzzy Automatic Threshold Update that is robust to illumination changes and slight shadow problems. The system incorporates a scene analysis scheme to automatically update the Learning Rates values of the BS model considering three possible scene situations. In order to improve the identification of dynamic objects, an Optical Flow algorithm analyzes the dynamic regions detected by the BS model, whose identification was not complete because of camouflage issues, and it defines the complete object based on similar velocities and direction probabilities. These regions are then used as the input needed by a Matte algorithm that will improve the definition of the dynamic object by minimizing a cost function. Among the original contributions of this work are; an adapting fuzzy-neural segmentation model whose thresholds and learning rates are adapted automatically according to the changes in the video sequence and the automatic improvement on the segmentation results based on the Matte algorithm and Optical flow analysis. Findings demonstrate that the proposed system produces a competitive performance compared with state-of-the-art reported models by using BMC and Li databases.     

General-purpose curvilinear object detection with fuzzy mathematical morphology

Curvilinear object detection is the common denominator of several applications. Some illustrative examples are road detection from aerial or satellite images, human airways from volumetric 3D scans or vascular structures in eye-fundus images. In this work, we propose two general-purpose curvilinear object detectors that may serve as building blocks for application-specific systems. To do so, we employ fuzzy mathematical morphology operators due to their robustness with respect to uncertainty and noise, and the trade-off they offer between expressive power and computational requirements. The extraction of linear features is based on, respectively, the fuzzy hit-or-miss transform and the fuzzy top-hat transform. They can be customized depending on the width of the objects of interest. We compare these two approaches with other state-of-the-art, general-purpose curvilinear object detectors to highlight their strengths and shortcomings. Both detectors succeed at localizing the objects of interest in different greyscale images.     

Modeling manufacturing processes using a genetic programming-based fuzzy regression with detection of outliers

Fuzzy regression (FR) been demonstrated as a promising technique for modeling manufacturing processes where availability of data is limited. FR can only yield linear type FR models which have a higher degree of fuzziness, but FR ignores higher order or interaction terms and the influence of outliers, all of which usually exist in the manufacturing process data. Genetic programming (GP), on the other hand, can be used to generate models with higher order and interaction terms but it cannot address the fuzziness of the manufacturing process data. In this paper, genetic programming-based fuzzy regression (GP-FR), which combines the advantages of the two approaches to overcome the deficiencies of the commonly used existing modeling methods, is proposed in order to model manufacturing processes. GP-FR uses GP to generate model structures based on tree representation which can represent interaction and higher order terms of models, and it uses an FR generator based on fuzzy regression to determine outliers in experimental data sets. It determines the contribution and fuzziness of each term in the model by using experimental data excluding the outliers. To evaluate the effectiveness of GP-FR in modeling manufacturing processes, it was used to model a non-linear system and an epoxy dispensing process. The results were compared with those based on two commonly used FR methods, Tanka’s FR and Peters’ FR. The prediction accuracy of the models developed based on GP-FR was shown to be better than that of models based on the other two FR methods.     

Deep active learning with Weighting filter for object detection

Active learning has been demonstrated to be effective in reducing labeling costs by selecting the most valuable data from the unlabeled pool. However, the training data of the first epoch in almost all active learning methods is randomly selected, which will cause an instability learning process. Additionally, current active learning, especially uncertainty-based active learning methods, is prone to the problem of data bias because model learning inevitably prefers partial data. For the above issues, we propose Weighting filter (W-filter) tailored for object detection in this paper, which is an image filtering algorithm that can calculate the contribution of a single image to the neural network training as well as remove similar ones in the entire selected data to optimize the sampling results. We first use W-filter to select the training data of the first epoch, which can guarantee better performance and a more stable learning process. Then, we propose to resample the uncertain data from the perspective of the frequency domain to alleviate the problem of data bias. Finally, we redesign several classical uncertainty methods specifically for classification to make them more suitable for the task of object detection. We do rigorous experiments on standard benchmark datasets to validate our work. Several classical detectors such as Faster R-CNN, SSD, R-FCN, CenterNet, EfficientDet, and effective networks including ResNet, DarkNet, MobileNet are used in experiments, which shows our framework is detector-agnostic and network-agnostic and thus can meet any detection scenario.     

Multi-view fast object detection by using extended haar filters in uncontrolled environments

In this paper, we propose multi-view object detection methodology by using specific extended class of haar-like filters, which apparently detects the object with high accuracy in the unconstraint environments. There are several object detection techniques, which work well in restricted environments, where illumination is constant and the view angle of the object is restricted. The proposed object detection methodology successfully detects faces, cars, logo objects at any size and pose with high accuracy in real world conditions. To cope with angle variation, we propose a multiple trained cascades by using the proposed filters, which performs even better detection by spanning a different range of orientation in each cascade. We tested the proposed approach by still images by using image databases and conducted some evaluations by using video images from an IP camera placed in outdoor. We tested the method for detecting face, logo, and vehicle in different environments. The experimental results show that the proposed method yields higher classification performance than Viola and Jones’s detector, which uses a single feature for each weak classifier. Given the less number of features, our detector detects any face, object, or vehicle in 15 fps when using 4 megapixel images with 95% accuracy on an Intel i7 2.8 GHz machine.     

A unified learning framework for object detection and classification using nested cascades of boosted classifiers

In this paper a unified learning framework for object detection and classification using nested cascades of boosted classifiers is proposed. The most interesting aspect of this framework is the integration of powerful learning capabilities together with effective training procedures, which allows building detection and classification systems with high accuracy, robustness, processing speed, and training speed. The proposed framework allows us to build state of the art face detection, eyes detection, and gender classification systems. The performance of these systems is validated and analyzed using standard face databases (BioID, FERET and CMU-MIT), and a new face database (UCHFACE).