Robot guidance using computer vision

This paper describes a procedure for locating an autonomous robot vehicle in a three-dimensional space. The method is an extension of a two-dimensional technique described by Fukui. The method is simple, requires little computation and provides the unique three-dimensional position of the robot relative to a standard mark.     

A dependency-based search strategy for feature selection

Feature selection has become an increasingly important field of research. It aims at finding optimal feature subsets that can achieve better generalization on unseen data. However, this can be a very challenging task, especially when dealing with large feature sets. Hence, a search strategy is needed to explore a relatively small portion of the search space in order to find “semi-optimal” subsets. Many search strategies have been proposed in the literature, however most of them do not take into consideration relationships between features. Due to the fact that features usually have different degrees of dependency among each other, we propose in this paper a new search strategy that utilizes dependency between feature pairs to guide the search in the feature space. When compared to other well-known search strategies, the proposed method prevailed.     

Breast cancer diagnosis using genetic programming generated feature

This paper proposes a novel method for breast cancer diagnosis using the feature generated by genetic programming (GP). We developed a new feature extraction measure (modified Fisher linear discriminant analysis (MFLDA)) to overcome the limitation of Fisher criterion. GP as an evolutionary mechanism provides a training structure to generate features. A modified Fisher criterion is developed to help GP optimize features that allow pattern vectors belonging to different categories to distribute compactly and disjoint regions. First, the MFLDA is experimentally compared with some classical feature extraction methods (principal component analysis, Fisher linear discriminant analysis, alternative Fisher linear discriminant analysis). Second, the feature generated by GP based on the modified Fisher criterion is compared with the features generated by GP using Fisher criterion and an alternative Fisher criterion in terms of the classification performance. The classification is carried out by a simple classifier (minimum distance classifier). Finally, the same feature generated by GP is compared with a original feature set as the inputs to multi-layer perceptrons and support vector machine. Results demonstrate the capability of this method to transform information from high-dimensional feature space into one-dimensional space and automatically discover the relationship among data, to improve classification accuracy.     

Hybrid feature selection algorithm using symmetrical uncertainty and a harmony search algorithm

Microarray technology can be used as an efficient diagnostic system to recognise diseases such as tumours or to discriminate between different types of cancers in normal tissues. This technology has received increasing attention from the bioinformatics community because of its potential in designing powerful decision-making tools for cancer diagnosis. However, the presence of thousands or tens of thousands of genes affects the predictive accuracy of this technology from the perspective of classification. Thus, a key issue in microarray data is identifying or selecting the smallest possible set of genes from the input data that can achieve good predictive accuracy for classification. In this work, we propose a two-stage selection algorithm for gene selection problems in microarray data-sets called the symmetrical uncertainty filter and harmony search algorithm wrapper (SU-HSA). Experimental results show that the SU-HSA is better than HSA in isolation for all data-sets in terms of the accuracy and achieves a lower number of genes on 6 out of 10 instances. Furthermore, the comparison with state-of-the-art methods shows that our proposed approach is able to obtain 5 (out of 10) new best results in terms of the number of selected genes and competitive results in terms of the classification accuracy.     

A feature binding model in computer vision for object detection

Multimedia Tools and Applications - In this paper, the authors propose the “Feature Binding (FB)” strategy in computer vision, a method combined with the biological visual perception...     

Speech recognition using a stereo vision neural network model

This paper describes a new algorithm for speech recognition by using stereo vision pattern recognition equations with competition and cooperation. In our research, we applied recently developed 3-layered neural net (3LNN) equations to speech recognition. Our proposed acoustic models using these equations yield better recognition results than the hidden Markov model (HMM). When using a 216 (240) word database, stereo vision acoustic models gave 6.5% (6.6%) higher accuracy than HMMs. This work was presented, in part, at the Fourth International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–22, 1999     

3D head model retrieval in kernel feature space using HSOM

In this paper, we propose a novel 3D head model retrieval framework. Specifically, to facilitate better classification and retrieval, the original 3D head model representations are embedded into another kernel feature space in which kernel principal component analysis (kernel PCA) is then performed to search for the optimal basis representation. Based on the extracted nonlinear features, a hierarchical indexing structure for 3D model retrieval is constructed using the hierarchical self organizing map (HSOM). The proposed indexing structure clusters the database into a hierarchy so that head models are partitioned by coarse features initially and then by finer scale features at lower levels. The main motivation of adopting this approach is that subspace technique like kernel PCA provides an elegant mechanism to describe the 3D head models on multiple resolutions based on the choices for reconstruction error and the orthogonal property of the produced eigenvectors. To further enhance the performance, a fuzzy metric between the query and the feature vector associated with each node on the SOMs is adopted instead of the usual Euclidean metric. Only nodes that possess high fuzzy measure values will be considered further for retrieval. In this way, the fuzzy measure approach is able to pick up potential relevant models even though they may be distributed across a number of neighbouring nodes. In addition to model categorization, the topology-preserving property of HSOM also facilitates the exploration of the model database with the possibility for further knowledge discovery. The effectiveness of the proposed approach is verified by a set of simulation examples on a 3D head model database.     

Bang-bang control strategy using a tabular adaptive model

An adaptive-predictive model for nonlinear, finite settling-time processes has been described by Roy et al., This paper utilizes this model for the trajectory following control of both finite and infinite settling-time nonlinear systems with switched two-level input.     

Robot calibration using the CPC error model

The complete and parametrically continuous (CPC) robot kinematic modeling convention has no model singularities and allows the modeling of the robot base and tool in the same manner by which the internal links are modeled. These two properties can be utilized to construct robot kinematic error models employing the minimum number of kinematic error parameters. These error parameters are independent and span the entire geometric error space. The BASE and TOOL error models are derived as special cases of the regular CPC error model. The CPC error model is useful for both kinematic identification and kinematic compensation. This paper focuses on the derivation of the CPC error models and their use in the experimental implementation of robot calibration.     

Robot vision by a contour sensor with associative memory

Advancing automation can only cope with the rising cost of labour.For visual inspection a minicomputer sustained optical contour sensor checks automatically whether all contours of an assembled part are present and lie within prefixed tolerances.Automation of welding or machining often requires high precision feeding of parts, causing prohibitive costs and thus rendering automation uneconomical. The optical contour sensor catches edges without mechanical contact and controls the machining or welding process relative to these edges.With associative retrieval of data stored in a training phase, the contour sensor recognizes and positions straight parts in arbitrary orientations on a conveyor belt, even if they touch and partly cover each other. This allows automation of many pick-and-place operations at the inputs of automated production lines.     

3D fingerprint reconstruction system using feature correspondences and prior estimated finger model

The paper studies a 3D fingerprint reconstruction technique based on multi-view touchless fingerprint images. This technique offers a solution for 3D fingerprint image generation and application when only multi-view 2D images are available. However, the difficulties and stresses of 3D fingerprint reconstruction are the establishment of feature correspondences based on 2D touchless fingerprint images and the estimation of the finger shape model. In this paper, several popular used features, such as scale invariant feature transformation (SIFT) feature, ridge feature and minutiae, are employed for correspondences establishment. To extract these fingerprint features accurately, an improved fingerprint enhancement method has been proposed by polishing orientation and ridge frequency maps according to the characteristics of 2D touchless fingerprint images. Therefore, correspondences can be established by adopting hierarchical fingerprint matching approaches. Through an analysis of 440 3D point cloud finger data (220 fingers, 2 pictures each) collected by a 3D scanning technique, i.e., the structured light illumination (SLI) method, the finger shape model is estimated. It is found that the binary quadratic function is more suitable for the finger shape model than the other mixed model tested in this paper. In our experiments, the reconstruction accuracy is illustrated by constructing a cylinder. Furthermore, results obtained from different fingerprint feature correspondences are analyzed and compared to show which features are more suitable for 3D fingerprint images generation.     

Mobile robot navigation using vision and olfaction to search for a gas/odor source

This paper presents a new approach to search for a gas/odor source using an autonomous mobile robot. The robot is equipped with a CMOS camera, gas sensors, and airflow sensors. When no gas is present, the robot looks for a salient object in the camera image. The robot approaches any object found in the field of view, and checks it with the gas sensors to see if the object is releasing gas. On the other hand, if the robot detects the presence of gas while wandering around the area, it turns toward the direction of the wind that carries the gas. The robot then looks for any visible object in that direction. These navigation strategies are implemented into the robot under the framework of the behavior-based subsumption architecture. Experimental results on the search for a leaking bottle in an indoor environment are presented to demonstrate the validity of the navigation strategies.     

3-D position sensing using a passive monocular vision system

Passive monocular 3-D position sensing is made possible by a new calibration scheme that relates depth to focus blur through a composite lens and aperture model. The calibration technique enables the recovery of absolute 3-D position coordinates from image coordinates and measured focus blur. A geometric model of the camera's position and orientation in space is used to transform the camera's imaging coordinates into world coordinates. The relationship between the world coordinate system and the screen coordinate system which includes the amount of focus blur, is developed by modeling the camera imaging arrangement. The modeling proceeds first through the perspective view from a pinhole camera located anywhere in space. The camera's lens and aperture system is investigated to find the relationship between depth and focus blur. The aspect ratio of the frame image is considered. Position accuracies comparable to those in stereo based vision systems are possible without the need for solving the difficult point of correspondence problem     

3-D model building for computer vision

This paper presents a Computer-Aided Geometric Design (CAGD) based approach for building 3-D models. A new method is given which allows the points on the surface of the designed object to be sampled at the desired resolution. The resulting data structure includes 3-D coordinates of the points, surface normals and neighborhood information.     

3D content-based search using sketches

This paper presents a novel interactive framework for 3D content-based search and retrieval using as query model an object that is dynamically sketched by the user. In particular, two approaches are presented for generating the query model. The first approach uses 2D sketching and symbolic representation of the resulting gestures. The second utilizes non-linear least squares minimization to model the 3D point cloud that is generated by the 3D tracking of the user’s hands, using superquadrics. In the context of the proposed framework, three interfaces were integrated to the sketch-based 3D search system including (a) an unobtrusive interface that utilizes pointing gesture recognition to allow the user manipulate objects in 3D, (b) a haptic–VR interface composed by 3D data gloves and a force feedback device, and (c) a simple air–mouse. These interfaces were tested and comparative results were extracted according to usability and efficiency criteria.     

Automatic feature design for optical character recognition using an evolutionary search procedure

An automatic evolutionary search is applied to the problem of feature extraction in an OCR application. A performance measure based on feature independence is used to generate features which do not appear to suffer from peaking effects [17]. Features are extracted from a training set of 30 600 machine printed 34 class alphanumeric characters derived from British mail. Classification results on the training set and a test set of 10 200 characters are reported for an increasing number of features. A 1.01 percent forced decision error rate is obtained on the test data using 316 features. The hardware implementation should be cheap and fast to operate. The performance compares favorably with current low cost OCR page readers.     

一种利用特征选择改进的行人检测模型

标准HOG模型在行人检测领域中最为经典,相比于标准模型中整齐划一的block,不同尺寸的block可以获得更多的细节信息。首先,在去除上下文背景的32×96尺寸模型基础上设计144个block特征;然后,提出类Fisher比计算block类别区分力;最后,利用NMS方法选出24个block,串接为1 854维的行人检测模型。实验结果表明,该利用特征选择改进的行人检测模型获得了显著的性能提升。     

Edge detection and linear feature extraction using a 2-D randomfield model

The edge-detection problem is posed as one of detecting step discontinuities in the observed correlated image, using directional derivatives estimated with a random field model. Specifically, the method consists of representing the pixels in a local window by a 2-D causal autoregressive (AR) model, whose parameters are adaptively estimated using a recursive least-squares algorithm. The directional derivatives are functions of parameter estimates. An edge is detected if the second derivative in the direction of the estimated maximum gradient is negatively sloped and the first directional derivative and a local estimate of variance satisfy some conditions. Because the ordered edge detector may not detect edges of all orientations well, the image scanned in four different directions, and the union of the four edge images is taken as the final output. The performance of the edge detector is illustrated using synthetic and real images. Comparisons to other edge detectors are given. A linear feature extractor that operates on the edges produced by the AR model is presented