Scene Recognition by Hyperspectral Ratio Indexing: How Many Channels Are Necessary?

This paper is concerned with the problem of feature point registration and scene recognition from images under weak perspective transformations which are well approximated by affine transformations and under possible occlusion and/or appearance of new objects. It presents a set of local absolute affine invariants derived from the convex hull of scattered feature points (e.g., fiducial or marking points, corner points, inflection points, etc.) extracted from the image. The affine invariants are constructed from the areas of the triangles formed by connecting three vertices among a set of four consecutive vertices (quadruplets) of the convex hull, and hence do make direct use of the area invariance property associated with the affine transformation. Because they are locally constructed, they are very well suited to handle the occlusion and/or appearance of new objects. These invariants are used to establish the correspondences between the convex hull vertices of a test image with a reference image in order to undo the affine transformation between them. A point matching approach for recognition follows this. The time complexity for registering L feature points on the test image with N feature points of the reference image is of order O(N x L). The method has been tested on real indoor and outdoor images and performs well.

Color-based object recognition

Object recognition is of fundamental importance in computer vision. In a few years, pedestrian detection, car detection, and more generally scene recognition will likely be reliable enough to allow fully-automated car navigation, and the human driver will be relegated to the back seat to sip his coffee. In this thesis we are interested in recognizing individual objects and categories. In order to reduce the volume of information one has to process, images are characterized by sets of features. These features, also called interest points, are targeted at image locations with high local information content. Various systems for detecting interest points and for describing the local image appearance near these points, have been proposed in the last two decades. We investigate which combinations from this plethora of detectors and descriptors, are most suited for object recognition tasks. On to the problem of object recognition, we are first interested in recognizing individual objects. In a few years, one can imagine that customers in shops, will take with their cell phone a picture of a product that looks interesting, send it to a remote server with a huge database of individual objects, and get back information about that specific product. We propose a system for individual object recognition, inspired from previous work on coarse-to-fine recognition. All steps of the recognition process are translated into principled probabilistic terms, which allows us to outperform a state-of-the-art commercial system for individual recognition. Regarding categories, faces are probably the category that has received the most attention in computer vision literature. Here we propose a system to recognize images of the same individual in large databases of images. This can be of high interest when looking for images of a given person over the internet. Our method's advantage is that it works on real-world images, as opposed to the face databases from the literature, collected in laboratories with controlled lighting, pose and background conditions. Finally, we are interested in recognition of object categories in general. Using support vector machines for the classification task, we propose a features-based kernel that improves recognition performance on object categories.

In Image Processing, the problem of Object Recognition is regarded as difficult. It's an important aspect of PC vision because so many PC vision programmes rely on it for effectiveness. To address this issue, a number of identifying terminology and frameworks have been discussed for quite some time. The purpose of this paper is to give a briefoverview of a range of platforms in the field of computer vision and object recognition. For the most part this paper covers a relatively mature service from AWS(Amazon Web Services), Amazon Rekognition which is easy to integrate into other services like Lambda, providing huge volume of details in its analysis. The paper incorporates different viewpoints that have been utilized by various analysts for object spotting and recognition. Rekognition is able to recognise objects and scenarios within photographs in this article, returning a confidence measure ranging from 0 to 100% for each label returned. It accomplishes this by using AWS’ Python client Boto3 and the detect labels method. This works by supplying an image, a limit on the number of labels to return, and a confidence level for filtering out ambiguous results.

Computer vision systems based on convolutional neural networks are being rapidly introduced in the field of precision agriculture to solve the problem of scene recognition. Convolutional networks allow performing high-precision recognition, but a significant problem is the expensive process of adapting the network to new conditions. This article proposes a method of fast adaptation of the trained network to minor changes in the source domain without annotating new data. This method is known as Adversarial Domain Adaptation, in the current paper it is applied to the problem of agricultural scene recognition in automated harvesting. The initial training procedure is modified for parallel training of an additional subnet on unannotated data, which makes it possible to compensate the domain shift due to adversarial training. This approach allows us to monotonically increase the quality of all recognized classes of objects and to enhance the stability of CNN model.

As we move through our environment, we encounter familiar objects from various viewpoints. Despite the ensuing variability of the images projected onto the retina, we have seemingly little difficulty when it comes to recognizing objects we encounter. We can, however, see how the objects are oriented, suggesting that object recognition is to a certain degree dissociable from perception of other object “features” such as orientation. Changes in orientation of objects, particularly inversion, can also affect how we perceive the objects. A particularly illustrative example (shown in Figure ​Figure1)1) is that of the Thatcher illusion (Thompson, 1980), where the grotesque appearance of a face with its inverted eyes and mouth is “hidden” when the whole face is also inverted. The percept itself, therefore, is affected by the change in orientation. In addition, there are also subtle effects of viewpoint changes on object recognition itself. For example, identifying rotated objects is more difficult when they are briefly presented than when viewing time is unlimited (Lawson and Jolicoeur, 2003), and identifying a face is considerably more difficult the face has been inverted (Yin, 1969), as is discrimination between characters “b” and “d,” or “p” and “q” which requires (physical or mental) rotation of the characters to upright, before we can be certain which letter we are looking at (Corballis and McLaren, 1984). Figure 1 Unaltered and “thatcherized” version of Margaret Thatcher's face. The grotesque appearance of the face when its eyes and mouth are inverted is hidden by the inversion of the whole image. Rotating the pictures to upright makes discrimination ... These subtle, yet persistent, effects of viewpoint changes on perception and recognition arise as a consequence of how visual object processing is handled by the brain. Here, I discuss how neural mechanisms underlying visual processing give rise to perception and recognition which can be both viewpoint dependent and viewpoint invariant depending on the timing of those processes, as well as specific task demands or current “perceptual goals” of an individual. To do so, I will firstly explain how temporal dynamics of low-level visual processing may give rise to impaired recognition at short viewing latencies and suggest that this may also relate to effects of viewpoint changes on perceptual experience. I will then discuss how the perceptual goals of an individual determines whether recognition is accomplished in viewpoint invariant or dependent manner with a particular focus on cognitive operations thought to be subserved by ventral and dorsal visual streams, namely object recognition and mental rotation, respectively.

Model-based object recognition has been a very active research field in Computerter Vision during the past ten years. Several excellent survey papers have been published, for example, [10.1,2]. Crimson has published a book [10.3] describing an extended series of experiments, carried out by himself and his colleagues at MIT, on the role of geometry in solving the object recognition and localization problem. Their approach is mainly based on the search in the interpretation tree, as briefly presented in Sect. 6.1. One chapter of the book by Faugeras [10.4] is also devoted to this problem based in detail with this immense subject. We want simply to adapt our motion-determination algorithm developed in Chap. 7 to solve some primitive object recognition problems.

3-D object recognition is a process of matching an object to a scene description to determine the object’s identity and/or its pose (position and orientation) in space. The problem of object recognition can be separated into two closely related subproblems — that of model building and that of recognition. Object recognition using multiple-view approach is achieved by finding a best match between the description of object projection and one of the model descriptions in the database. An object is modeled by its 2-D projections as seen from a set of predetermined viewpoints uniformly distributed on a view sphere enclosing the object. In our experiments, an icosahedron (twenty-sided) is used to approximate the view sphere. The method to search the model database is crucial to the performance of the recognition process. To recognize an object, a coarse-to-fine search strategy is adopted to reduce the processing time. At the coarse search stage, a small set of views most similar to the object in the scene is located. In most cases, this step vastly decreases the search space. The fine (or exhaustive) search process starts with these located views and compares the topology of the object in the scene with the projections rendered by the neighboring viewpoints of the located viewpoints until a best match is found. In this paper, a FKCN model which is an integration of Fuzzy c-Means (FCM) and Kohonen clustering networks (KCNs) is proposed to exploit the parallelism at the coarse search stagein object recognition, where the learning rate for Kohonen updating is proposed to be: $$\alpha _{ik,t}= (u_{ik,t} )^m t$$ where \(\alpha _{ik,t}= \left( {\sum {\left( {\parallel x_k- v_i \parallel _A /\parallel _{x_k }- v_j \parallel _A } \right)^{2/(m - 1)} } } \right)^{ - 1}\) by minimizing \(\sum\limits_i {\sum\limits_{\mathfrak{k}^u ik} m } \left( {\parallel x_k- v_i \parallel _A } \right)^2\),but weighting exponent m is a function of t, the iterate number, i.e. m = mt = (m0+tΔm) (an increasing strategy). Feature vectors are first extracted from each view. Then a FKCN clusters these feature vectors to get cluster centers, each of which is regarded as a prototype of some similar views. Finally, a feature vector from an input view is compared to the cluster centers instead of all views and finds the potential candidates which are clustered into the closest cluster center in order to achieve the goal of reducing search space.

Thai text localization and recognition in natural scenes is still a grand challenge in current applications. However, the efficiency of recognition rates depends on text localization, i.e., the higher purity of text-background decomposition leads to the higher accuracy rate of character recognition. In order to achieve this purpose, the text-background decomposition methods, namely adaptive boundary clustering (ABC) and n-point boundary clustering (n-PBC), are proposed to improve a precision of text localization. These methods are evaluated by self-en-tropy for purity measure. Based on 300 test images, the experimental results demonstrate that the ABC method achieves the very low self-entropy, i.e., the low self-entropy implies the good decomposition of text and background. Furthermore, based on 8,077 characters in natural scene test images, the ABC method helps increase the precision of text localization and improves the accuracy rate of character recognition, when compared to the conventional methods.

Comparative perspectives on multiple cortical visual systems

Active/space-variant object recognition

Robust scene recognition using a GA and real-world raw-image

Ratios of excitations in each cone-photoreceptor class produced by light reflected from pairs of surfaces in a scene are almost invariant under natural illuminant changes. The stability of these spatially defined ratios may explain the remarkable ability of human observers to efficiently discriminate illuminant changes from changes in surface reflectances. Spatial cone-excitation ratios are not, however, exactly invariant. This study is concerned with observers' sensitivity to these invariance violations. Simulations of Mondrian paintings with either 49 or two natural surfaces under Planckian illuminants were presented as images on a computer-controlled display in a two-interval experimental design: in one interval, the surfaces underwent an illuminant change; in the other interval, the surfaces underwent the same change but the images were then corrected so that, for each cone class, ratios of excitations were preserved exactly. Although the intervals with corrected images corresponded individually to highly improbable natural events, observers systematically misidentified them as containing the illuminant changes, the probability of error increasing as the violation of invariance in the other interval increased. For the range of illuminants and surfaces tested, sensitivity to violations of invariance was found to depend on cone class: it was greatest for long-wavelength-sensitive cones and least for short-wavelength-sensitive cones. Spatial cone-excitation ratios, or some closely related quantities, seem to be the cues preferred by observers for making inferences about surface illuminant changes.

Unsupervised shape discovery using synchronized spectral networks

We consider the problem of object recognition via local geometric feature matching in the presence of sensor uncertainty, occlusion, and clutter. We present a general formulation of the problem and a polynomial-time algorithm which guarantees finding all geometrically feasible interpretations of the data, modulo uncertainty, in terms of the model. This formulation applies naturally to problems involving both 2D and 3D objects.The primary contributions of this work are the presentation of a robust, provably correct, polynomial-time approach to this class of recognition problems and a demonstration of its practical application; and the development of a general framework for understanding the fundamental nature of the geometric feature matching problem. This framework provides insights for analyzing and improving previously proposed recognition approaches, and enables the development of new algorithms.