Scale Invariant Recognition Research Articles

Distortion, rotation and scale invariant recognition of hollow Hindi characters

Distortion, rotation and scale invariant recognition of hollow Hindi characters

Meta features-based scale invariant OCR decision making using LSTM-RNN

Urdu optical character recognition (OCR) is a complex problem due to the nature of its script, which is cursive. Recognizing characters of different font sizes further complicates the problem. In this research, long short term memory-recurrent neural network (LSTM-RNN) and convolution neural network (CNN) are used to recognize Urdu optical characters of different font sizes. LSTM-RNN is trained on formerly extracted feature sets, which are extracted for scale invariant recognition of Urdu characters. From these features, LSTM-RNN extracts meta features. CNN is trained on raw binary images. Two benchmark datasets, i.e. centre for language engineering text images (CLETI) and Urdu printed text images (UPTI) are used. LSTM-RNN reveals consistent results on both datasets, and outperforms CNN. Maximum 99% accuracy is achieved using LSTM-RNN.

Affine‐scale invariant feature transform and two‐dimensional principal component analysis: a novel framework for affine and scale invariant face recognition

Face recognition (FR) is one of the most effervescent fields of research with extensive applications that span numerous domains, and it stands resolutely as one of the most challenging problems in computer vision. The accuracy of FR systems is severely affected when two images under consideration for a match, vary in their scale and/or affine angles. The prevalent affine and scale invariant recognition systems have been predominantly developed only for objects, and hence in this study, the authors propose a novel approach for faces based on the affine‐SIFT (ASIFT) and two‐dimensional principal component analysis (2DPCA) techniques, to accomplish the formidable task of facial image recognition, invariant of scale and affine angles, i.e. the ability to simulate with enough accuracy, all the distortions caused by the differences in resolution and the variation of the camera optical axis direction. In the formulation of ASIFT‐2DPCA, they investigate three different variants of 2DPCA: classical 2DPCA, quaternion 2DPCA and sparse 2DPCA to gauge as to which is more effective. The authors'experimentations will demonstrate that the proposed approach can robustly handle affine and scale variations, and hence provide better accuracy and matching performance than the state‐of‐the‐art methodologies.

A systematic evaluation of the scale invariance of texture recognition methods

A large variety of well-known scale-invariant texture recognition methods is tested with respect to their scale invariance. The scale invariance of these methods is estimated by comparing the results of two test setups. In the first test setup, the images of the training and evaluation set are acquired under same scale conditions and in the second test setup, the images in the evaluation set are gathered under different scale conditions than those of the training set. For the first test setup, scale invariance is not needed, whereas for the second test setup, scale invariance is obviously crucial. The difference between the results of these two test setups indicates the scale invariance of a method (the higher the scale invariance the lower the difference). The scale invariance of the methods is additionally estimated by analyzing the similarity of the feature vectors of images and their scaled versions. Additionally to the scale invariance, we also test eventual viewpoint and illumination invariance of the methods. As texture databases for our tests we use the KTH-TIPS database and the CUReT database. Results imply that many of the considered methods are not as scale-invariant as expected.

Distortion-invariant recognition of volume holographic correlator based on morphological algorithm and synthetic discriminant function

We proposed a novel method based on mathematical morphological algorithm and space domain synthetic discriminant function (SDF) for distortion-invariant recognition of volume holographic correlator (VHC). To suppress the effect of pattern-dependent behavior, a new morphological algorithm is introduced, which can process the gray-scale images into strong and clean edge maps without redundancy and irrelevant detail. Using these edge maps, SDF filters are synthesized for detecting distorted targets on VHC system. Experimental results demonstrate that the proposed method can achieve both rotation and scale invariant recognition.

2P1-J04 スケールと位置に不変な物体識別を行う脳型視覚システム(ロボットビジョン(2))

We have developed a visual system achieving scale and position invariant object classification. The system includes a silicon retina, a field-programmable gate array (FPGA), and a personal computer (PC). Its algorithm is based on the HMAX model, which is a hierarchical model of object recognition in the visual cortex and offers scale and position invariant recognition. In order to perform a lot of spatial filtering required by the model effectively, we employed a resistive network. The output of the system was examined using visual stimuli displayed on a LCD monitor, and the system was successful in classifying several figures and alphabetical letters independently of scale and position of the target.

A continuous GA+LDA for training set enhancement in illumination and scale invariant face recognition

The face recognition performance of linear discriminant analysis (LDA) is considerably reduced by illumination and scale changes. Actually, performance of LDA is significantly affected by the number of images of each individual in the training set. Hence, the idea presented in this paper is to generate new images with illumination and scale changes, from the available frontal images in the training set, and add to training set such that the recognition rate of LDA is maximised over both the training and test sets. A continuous genetic algorithm is used to find the optimal sets of illumination and scale change parameters that make the success of LDA invariant to these facial variations. Compared to the application of LDA over the initially given face database, experimental evaluations demonstrated that the performance of LDA is significantly enhanced over the test set for illumination and scale changes, without decreasing the success for other test cases.

Novel moment invariants for improved classification performance in computer vision applications

A novel set of moment invariants based on the Krawtchouk moments are introduced in this paper. These moment invariants are computed over a finite number of image intensity slices, extracted by applying an innovative image representation scheme, the image slice representation (ISR) method. Based on this technique an image is decomposed to a several non-overlapped intensity slices, which can be considered as binary slices of certain intensity. This image representation gives the advantage to accelerate the computation of image's moments since the image can be described in a number of homogenous rectangular blocks, which permits the simplification of the computation formulas. The moments computed over the extracted slices seem to be more efficient than the corresponding moments of the same order that describe the whole image, in recognizing the pattern under processing. The proposed moment invariants are exhaustively tested in several well known computer vision datasets, regarding their rotation, scaling and translation (RST) invariant recognition performance, by resulting to remarkable outcomes.

Adaptive multiple sets of CSS features for hand posture recognition

In this paper, an adaptive feature extraction approach based on curvature scale space (CSS) is presented for translation, scale, and rotation invariant recognition of hand postures. First, hands are segmented from hand posture images into binary silhouettes and then binary hand contours are computed. CSS images are then used to represent the contours of hand postures. In particular, adaptive multiple sets of CSS features are extracted to address the problem of deep concavities in the contours of hand postures. Finally, 1-nearest neighbor techniques are used to perform adaptive multiple sets of CSS feature matching for hand posture identification. Results indicate that the proposed approach performs well in the recognition of hand postures. And, the proposed approach is more accurate than previous methods which were based on conventional features. The proposed technique could be useful in improving the recognition of hand postures.

Unbalanced Scaling and Rotation Invariant Recognition by

Unbalanced Scaling and Rotation Invariant Recognition by

Shift- and scale-invariant pattern recognition using morphological phase-only correlation

We propose a non-linear correlation to realize scale-invariant recognition, called shift- and scale-invariant morphological phase-only correlation (SSIMPC), which is a combination of radial harmonic filter (RHF) and morphological phase-only correlation (MPC). We form SSIMPC using phase-only RHFs (PORHF) instead of common RHFs in every sub-correlations of morphological radial harmonic correlation (MRHC). Computer simulation results demonstrate that the performance of SSIMPC is better than that of MRHC in discrimination and robustness against non-Gaussian noise, such as salt-and-pepper noise and cluttered background, and above of all, SSIMOC realizes approximately full scale-invariance. In addition, we devise an optoelectronic scheme, which is identical to the setup for MPC, to implement SSIMPC.

Simple Gabor feature space for invariant object recognition

Invariant object recognition is one of the most challenging problems in computer vision. The authors propose a simple Gabor feature space, which has been successfully applied to applications, e.g., in invariant face detection to extract facial features in demanding environments. In the proposed feature space, illumination, rotation, scale, and translation invariant recognition of objects can be realized within a reasonable amount of computation. In this study, fundamental properties of Gabor features, construction of the simple feature space, and invariant search operations in the feature space are discussed in more detail.

Optical pattern recognition algorithms, architecture, and applications: introduction to the feature issue

This issue of Applied Optics features eight papers in the areas of optical pattern recognition. They range from new algorithms for improved classification, rotation and scale invariant recognition to novel architectures and applications of optical correlation filters in information processing.

Scale-invariant recognition of three-dimensional objects by use of a quasi-correlator.

A method of scale-invariant recognition of three-dimensional (3-D) objects is presented. Several images of the observed scene are recorded under white-light illumination from several different points of view and compressed into a single complex two-dimensional matrix. After filtering with a single scale-invariant filter, the resultant function is then coded into a computer-generated hologram (CGH). When this CGH is coherently illuminated, a correlation space is reconstructed in which light peaks indicate the existence and location of true targets in the tested 3-D scene. The light peaks are detectable for different sizes of the true objects, as long as they are within the invariance range of the filter. Experimental results in a complete electro-optical system are presented, and comparisons with other systems are investigated by use of computer simulation.

A visual system for invariant recognition in animated image sequences

The problem of invariant recognition in simple animated image sequences is investigated using a biologically inspired model. It integrates a bottom-up attention module, a synchronization-based segmentation mechanism, a normalization network and a recognition module. The results show how the system provides the following properties: (1) change-based attention in animated sequences, (2) multiple object segmentation, and (3) translation and scale invariant recognition.

Shift- and scale-invariant recognition of contour objects with logarithmic radial harmonic filters

The phase-only logarithmic radial harmonic (LRH) filter has been shown to be suitable for scale-invariant block object recognition. However, an important set of objects is the collection of contour functions that results from a digital edge extraction of the original block objects. These contour functions have a constant width that is independent of the scale of the original object. Therefore, since the energy of the contour objects decreases more slowly with the scale factor than does the energy of the block objects, the phase-only LRH filter has difficulties in the recognition tasks when these contour objects are used. We propose a modified LRH filter that permits the realization of a shift- and scale-invariant optical recognition of contour objects. The modified LRH filter is a complex filter that compensates the energy variation resulting from the scaling of contour objects. Optical results validate the theory and show the utility of the newly proposed method.

Triplet geometric representation: a novel scale, translation and rotation invariant feature representation based on geometric constraints for recognition of 2D object features

We present a novel representation for scale, translation and rotation independent recognition of 2D object features based on the invariance properties of the included angles of a triangle which we exploit to construct signature histograms of local shape. We describe the practical implementation of this new technique together with its properties, and present a statistical quantification of performance in the presence of: fragmentation, additive noise and clutter. The scale-invariant properties are assessed, the results of which imply a fundamental limit on scale-invariant recognition from a single model.

Scale-invariant image recognition based on higher-order autocorrelation features

We propose a framework and a complete implementation of a translation and scale-invariant image recognition system for natural indoor scenes. The system employs higher-order autocorrelation features of scale space data which permit linear classification. An optimal linear classification method is presented, which is able to cope with a large number of classes represented by many, as well as very few samples. In the course of the analysis of our system, we examine which numerical methods for feature transformation and classification show sufficient stability to fulfill these demands. The implementation has been extensively tested. We present the results of our own application and several classification benchmarks.

Polynomial expansion for shift- and one- or two-dimensional scale-invariant pattern recognition

A polynomial expansion is suggested for achieving optical invariant pattern recognition. The expansion results in a real function and thus is theoretically able to be implemented under both coherent and spatially incoherent illumination. One obtains the expansion after applying the Gram-Schmidt algorithm on the Laurent's series in order to achieve orthonormality. The initial Laurent term with which we apply the Gram-Schmidt procedure is chosen according to the desired expansion order. The use of the polynomial expansion is demonstrated for shift- and one-dimensional scale-invariant pattern recognition as well as for shift-and two-dimensional scale-invariant recognition.

Similarity-invariant signatures for partially occluded planar shapes

A methodology is described for associating local invariant signature functions to smooth planar curves in order to enable their translation, rotation, and scale-invariant recognition from arbitrarily clipped portions. The suggested framework incorporates previous approaches, based on locating inflections, curvature extrema, breakpoints, and other singular points on planar object boundaries, and provides a systematic way of deriving novel invariant signature functions based on curvature or cumulative turn angle of curves. These new signatures allow the specification of arbitrarily dense feature points on smooth curves, whose locations are invariant under similarity transformations. The results are useful for detecting and recognizing partially occluded planar objects, a key task in low-level robot vision.