Approach For Object Recognition Research Articles

A Bottom-up Approach for Visual Object Recognition on FPGA based Embedded Multiprocessor Architecture

This paper presents an object recognition approach of outdoor autonomous systems identifying the nature of the interested object when observing an image. Therefore, seeking for effective and robust recognition method, the proposed approach is performed using a novel saliency based feature detector/descriptor which is combined with an object classifier to identify the nature of objects in an indoor or an outdoor environment. As known, bottom-up visual attention computational models need a considerable computational power and communication cost. A major challenge in this work is to deal with such image processing applications managing a large amount of the information processing and to work within real-time requirements by improving the processing speed. Based on interesting approach designing specific architectures for parallelism, this paper presents a solution for rapid prototyping of saliency-based object recognition applications. In order to meet computation and communication requirement, the developed pipelined architectures are composed of identical processing modules which can work concurrently with distributed memories and compute in parallel several sequential tasks with a high computational cost. We present hardware implementations with performance results on an Xilinx System-on-Programmable Chip (SoPC) target. The experimental results including execution times and application speedups as well as requirements in terms of computing resources show that the proposed homogeneous network of processors is efficient for embedding the proposed image processing application.

Task-Driven Progressive Part Localization for Fine-Grained Object Recognition

The problem of fine-grained object recognition is very challenging due to the subtle visual differences between different object categories. In this paper, we propose a task-driven progressive part localization (TPPL) approach for fine-grained object recognition. Most existing methods follow a two-step approach that first detects salient object parts to suppress the interference from background scenes and then classifies objects based on features extracted from these regions. The part detector and object classifier are often independently designed and trained. In this paper, our major finding is that the part detector should be jointly designed and progressively refined with the object classifier so that the detected regions can provide the most distinctive features for final object recognition. Specifically, we develop a part-based SPP-net (Part-SPP) as our baseline part detector. We then establish a TPPL framework, which takes the predicted boxes of Part-SPP as an initial guess, and then examines new regions in the neighborhood using a particle swarm optimization approach, searching for more discriminative image regions to maximize the objective function and the recognition performance. This procedure is performed in an iterative manner to progressively improve the joint part detection and object classification performance. Experimental results on the Caltech-UCSD-200-2011 dataset demonstrate that our method outperforms state-of-the-art fine-grained categorization methods both in part localization and classification, even without requiring a bounding box during testing.

An Improved Bag-of-Features Approach for Object Recognition from Natural Images

An Improved Bag-of-Features Approach for Object Recognition from Natural Images

Support subspaces method for synthetic aperture radar automatic target recognition

This article offers a new object recognition approach that gives high quality using synthetic aperture radar images. The approach includes image preprocessing, clustering and recognition stages. At the image preprocessing stage, we compute the mass centre of object images for better image matching. A conjugation index of a recognition vector is used as a distance function at clustering and recognition stages. We suggest a construction of the so-called support subspaces, which provide high recognition quality with a significant dimension reduction. The results of the experiments demonstrate that the proposed method provides higher recognition quality (97.8%) than such methods as support vector machine (95.9%), deep learning based on multilayer auto-encoder (96.6%) and adaptive boosting (96.1%). The proposed method is stable for objects processed from different angles.

Improved contour detection model with spatial summation properties based on nonclassical receptive field

The responses of cortical neurons to a stimulus in a classical receptive field (CRF) can be modulated by stimulating the non-CRF (nCRF) of neurons in the primary visual cortex (V1). In the very early stages (at around 40 ms), a neuron in V1 exhibits strong responses to a small set of stimuli. Later, however (after 100 ms), the neurons in V1 become sensitive to the scene’s global organization. As per these visual cortical mechanisms, a contour detection model based on the spatial summation properties is proposed. Unlike in previous studies, the responses of the nCRF to the higher visual cortex that results in the inhibition of the neuronal responses in the primary visual cortex by the feedback pathway are considered. In this model, the individual neurons in V1 receive global information from the higher visual cortex to participate in the inhibition process. Computationally, global Gabor energy features are involved, leading to the more coherent physiological characteristics of the nCRF. We conducted an experiment where we compared our model with those proposed by other researchers. Our model explains the role of the mutual inhibition of neurons in V1, together with an approach for object recognition in machine vision.

A novel approach for shape-based object recognition with curvelet transform

In this work, we revisit multi-resolution analysis (MRA) methods for object recognition. We find an optimal sparse representation of an image using a second-generation Fast Discrete Curvelet Transform (FDCT) and present a novel curvelet approach based on thin plate splines (TPS). Measurement of local deformation at each FDCT coefficient is detailed. Specific deformations in the TPS-based curve-let transformation are identified by minimization (Curvature) of total bending energy. Shape toning is processed through the Euclidean distance. Results of implementation of proposed descriptor for five standard databases are analyzed, while their comparison with other revealed relative efficiency.

Node Detection and Internode Length Estimation of Tomato Seedlings Based on Image Analysis and Machine Learning.

Seedling vigor in tomatoes determines the quality and growth of fruits and total plant productivity. It is well known that the salient effects of environmental stresses appear on the internode length; the length between adjoining main stem node (henceforth called node). In this study, we develop a method for internode length estimation using image processing technology. The proposed method consists of three steps: node detection, node order estimation, and internode length estimation. This method has two main advantages: (i) as it uses machine learning approaches for node detection, it does not require adjustment of threshold values even though seedlings are imaged under varying timings and lighting conditions with complex backgrounds; and (ii) as it uses affinity propagation for node order estimation, it can be applied to seedlings with different numbers of nodes without prior provision of the node number as a parameter. Our node detection results show that the proposed method can detect 72% of the 358 nodes in time-series imaging of three seedlings (recall = 0.72, precision = 0.78). In particular, the application of a general object recognition approach, Bag of Visual Words (BoVWs), enabled the elimination of many false positives on leaves occurring in the image segmentation based on pixel color, significantly improving the precision. The internode length estimation results had a relative error of below 15.4%. These results demonstrate that our method has the ability to evaluate the vigor of tomato seedlings quickly and accurately.

Edge feature based approach for object recognition

We address the problem of recognizing the object with distinctive edge features. For this purpose, a recognition approach based on local edge features is presented. First the edge features are detected in each image, and then its descriptor is computed to find the match features. Each match will give a vote with location, scale and orientation of the object. The recognition result can be found in the densest position in the vote space. Experimental results show that the presented method is robust and effective to the object with distinctive edge features.

Augmented reality three-dimensional object visualization and recognition with axially distributed sensing.

An augmented reality (AR) smartglass display combines real-world scenes with digital information enabling the rapid growth of AR-based applications. We present an augmented reality-based approach for three-dimensional (3D) optical visualization and object recognition using axially distributed sensing (ADS). For object recognition, the 3D scene is reconstructed, and feature extraction is performed by calculating the histogram of oriented gradients (HOG) of a sliding window. A support vector machine (SVM) is then used for classification. Once an object has been identified, the 3D reconstructed scene with the detected object is optically displayed in the smartglasses allowing the user to see the object, remove partial occlusions of the object, and provide critical information about the object such as 3D coordinates, which are not possible with conventional AR devices. To the best of our knowledge, this is the first report on combining axially distributed sensing with 3D object visualization and recognition for applications to augmented reality. The proposed approach can have benefits for many applications, including medical, military, transportation, and manufacturing.

物体認識のための3次元特徴量の研究動向

SUMMARY Recently, various kinks of three-dimensional (3D) imaging devices such as laser range finder or time-of-flight sensor become popular, so a lot of practical algorithms for recognizing 3D objects using “point cloud data” have been proposed. In this paper, we will introduce typical object recognition approaches and survey various kinds of 3D features proposed by many researchers. As for some important techniques, their principle and characteristics are explained in detail. Also we will mention about the local reference frame that is very important factor to realize stable feature description and accurate pose estimation in practical use.

Object Detection Based on Two Level Fast Matching

Shape template matching is an important approach in object detection and recognition. In this paper, we propose a fast and novel object detection method, which represents edge map contours with salient points and retrieves the target object by using a backtracking method with two stages from coarse matching to fine matching. Our method has two main contributions. One is we propose the way to represent contour structure with salient points. The other is that the object detection method proposed can directly operate on the real images, which improves its practicability. According to the experimental results, the proposed approach improves the speed than previous works.

Nonparametric Image Registration of Airborne LiDAR, Hyperspectral and Photographic Imagery of Wooded Landscapes

There is much current interest in using multi-sensor airborne remote sensing to monitor the structure and biodiversity of forests. This paper addresses the application of non-parametric image registration techniques to precisely align images obtained from multimodal imaging, which is critical for the successful identification of individual trees using object recognition approaches. Non-parametric image registration, in particular the technique of optimizing one objective function containing data fidelity and regularization terms, provides flexible algorithms for image registration. Using a survey of woodlands in southern Spain as an example, we show that non-parametric image registration can be successful at fusing datasets when there is little prior knowledge about how the datasets are interrelated (i.e. in the absence of ground control points). The validity of non-parametric registration methods in airborne remote sensing is demonstrated by a series of experiments. Precise data fusion is a prerequisite to accurate recognition of objects within airborne imagery, so non-parametric image registration could make a valuable contribution to the analysis pipeline.

A New Object Recognition Approach Using Combination of Texture, Color and Shape Features

This paper reports a new approach for recognizing objects by using combination of texture, color and shape features. Texture features were generated by applying statistical calculation on the image histogram. Color features were computed by using mean, standard deviation, skewness and kurtosis. Shape features were generated using combination of Shen features and basic shapes such as eccentricity and dispersion. The total features were used much less compared to approaches that involve orthogonal moments such as Krawtchouk moments, Zernike moments, or Tchebichef moments. Testing was done by using a dataset that contains 53 kinds of objects. All objects contained in the dataset were various things that can be found in supermarkets or produced by manufacturing. The result shows that the system gave 98.11% of accuracy rate.

Using an improved SIFT algorithm and fuzzy closed-loop control strategy for object recognition in cluttered scenes.

Partial occlusions, large pose variations, and extreme ambient illumination conditions generally cause the performance degradation of object recognition systems. Therefore, this paper presents a novel approach for fast and robust object recognition in cluttered scenes based on an improved scale invariant feature transform (SIFT) algorithm and a fuzzy closed-loop control method. First, a fast SIFT algorithm is proposed by classifying SIFT features into several clusters based on several attributes computed from the sub-orientation histogram (SOH), in the feature matching phase only features that share nearly the same corresponding attributes are compared. Second, a feature matching step is performed following a prioritized order based on the scale factor, which is calculated between the object image and the target object image, guaranteeing robust feature matching. Finally, a fuzzy closed-loop control strategy is applied to increase the accuracy of the object recognition and is essential for autonomous object manipulation process. Compared to the original SIFT algorithm for object recognition, the result of the proposed method shows that the number of SIFT features extracted from an object has a significant increase, and the computing speed of the object recognition processes increases by more than 40%. The experimental results confirmed that the proposed method performs effectively and accurately in cluttered scenes.

Recognizing multi-view objects with occlusions using a deep architecture

Image-based object recognition is employed widely in many computer vision applications such as image semantic annotation and object location. However, traditional object recognition algorithms based on the 2D features of RGB data have difficulty when objects overlap and image occlusion occurs. At present, RGB-D cameras are being used more widely and the RGB-D depth data can provide auxiliary information to address these challenges. In this study, we propose a deep learning approach for the efficient recognition of 3D objects with occlusion. First, this approach constructs a multi-view shape model based on 3D objects by using an encode–decode deep learning network to represent the features. Next, 3D object recognition in indoor scenes is performed using random forests. The application of deep learning to RGB-D data is beneficial for recovering missing information due to image occlusion. Our experimental results demonstrate that this approach can significantly improve the efficiency of feature representation and the performance of object recognition with occlusion.

A local approach for 3D object recognition through a set of size functions

In this paper, a local approach for 3D object recognition is presented. It is based on the topological invariants provided by the critical points of the 3D object. The critical points and the links between them are represented by a set of size functions obtained after splitting the 3D object into portions. A suitable similarity measure is used to compare the sets of size functions associated with the 3D objects. In order to validate our approach's recognition performance, we used different collections of 3D objects. The obtained scores are favourably comparable to the related work.

Object Recognition Based on Dual Tree Complex Wavelet Transform

Automated recognition of objects from images plays an important role in many computer vision systems such as robot navigation, object manipulation and content based image retrieval. In this study, an approach for object recognition based on Dual Tree Complex Wavelet Transform (DTCWT) is proposed. The proposed approach attempts to extract the detailed information of objects from the multi scale representation by DTCWT. The proposed system is tested on Columbia Object Image Library (COIL-100). All the objects are considered for the classification based on nearest neighbor classifier. The results show that the maximum recognition accuracy achieved by the proposed approach is 97.03%.

Innate pattern recognition and categorization in a jumping spider.

The East African jumping spider Evarcha culicivora feeds indirectly on vertebrate blood by preferentially preying upon blood-fed Anopheles mosquitoes, the vectors of human malaria1, using the distinct resting posture and engorged abdomen characteristic of these specific prey as key elements for their recognition. To understand perceptual categorization of objects by these spiders, we investigated their predatory behavior toward different digital stimuli - abstract ‘stick figure’ representations of Anopheles constructed solely by known key identification elements, disarranged versions of these, as well as non-prey items and detailed images of alternative prey. We hypothesized that the abstract images representing Anopheles would be perceived as potential prey, and would be preferred to those of non-preferred prey. Spiders perceived the abstract stick figures of Anopheles specifically as their preferred prey, attacking them significantly more often than non-preferred prey, even when the comprising elements of the Anopheles stick figures were disarranged and disconnected from each other. However, if the relative angles between the elements of the disconnected stick figures of Anopheles were altered, the otherwise identical set of elements was no longer perceived as prey. These data show that E. culicivora is capable of making discriminations based on abstract concepts, such as the hypothetical angle formed by discontinuous elements. It is this inter-element angle rather than resting posture that is important for correct identification of Anopheles. Our results provide a glimpse of the underlying processes of object recognition in animals with minute brains, and suggest that these spiders use a local processing approach for object recognition, rather than a holistic or global approach. This study provides an excellent basis for a comparative analysis on feature extraction and detection by animals as diverse as bees and mammals.

Sparse spatial coding: a novel approach to visual recognition.

Successful image-based object recognition techniques have been constructed founded on powerful techniques such as sparse representation, in lieu of the popular vector quantization approach. However, one serious drawback of sparse space-based methods is that local features that are quite similar can be quantized into quite distinct visual words. We address this problem with a novel approach for object recognition, called sparse spatial coding, which efficiently combines a sparse coding dictionary learning and spatial constraint coding stage. We performed experimental evaluation using the Caltech 101, Caltech 256, Corel 5000, and Corel 10000 data sets, which were specifically designed for object recognition evaluation. Our results show that our approach achieves high accuracy comparable with the best single feature method previously published on those databases. Our method outperformed, for the same bases, several multiple feature methods, and provided equivalent, and in few cases, slightly less accurate results than other techniques specifically designed to that end. Finally, we report state-of-the-art results for scene recognition on COsy Localization Dataset (COLD) and high performance results on the MIT-67 indoor scene recognition, thus demonstrating the generalization of our approach for such tasks.

Tracking of secondary and temporary objects in structural concrete work

Purpose– Previous research has shown that “Scan-vs-BIM” object recognition systems, which fuse three dimensional (3D) point clouds from terrestrial laser scanning (TLS) or digital photogrammetry with 4D project building information models (BIM), provide valuable information for tracking construction works. However, until now, the potential of these systems has been demonstrated for tracking progress of permanent structural works only; no work has been reported yet on tracking secondary or temporary structures. For structural concrete work, temporary structures include formwork, scaffolding and shoring, while secondary components include rebar. Together, they constitute most of the earned value in concrete work. The impact of tracking secondary and temporary objects would thus be added veracity and detail to earned value calculations, and subsequently better project control and performance. The paper aims to discuss these issues.Design/methodology/approach– Two techniques for recognizing concrete construction secondary and temporary objects in TLS point clouds are implemented and tested using real-life data collected from a reinforced concrete building construction site. Both techniques represent significant innovative extensions of existing “Scan-vs-BIM” object recognition frameworks.Findings– The experimental results show that it is feasible to recognise secondary and temporary objects in TLS point clouds with good accuracy using the two novel techniques; but it is envisaged that superior results could be achieved by using additional cues such as colour and 3D edge information.Originality/value– This article makes valuable contributions to the problem of detecting and tracking secondary and temporary objects in 3D point clouds. The power of Scan-vs-BIM object recognition approaches to address this problem is demonstrated, but their limitations are also highlighted.