Figure 1 - uploaded by Aaron Mavrinac
Content may be subject to copyright.
Source publication
1 It is desirable for automated object recognition using computer vision systems to emulate the human capacity for recognition of shapes invariant to vari-ous transformations. We present an algorithm, based on a Fuzzy Associative Database approach, which uses appropriately invariant metrics and a neu-ro-fuzzy inference method to accurately classify...
Contexts in source publication
Context 1
... the purpose of this description and throughout this work, the following convention is used for the world and image coordinate systems: lowercase x and y represent image coordinates with origin at the upper left corner of the image and positive axes right and down respectively, and uppercase X, Y, and Z represent world coordinates (which, unless otherwise specified, are mutually ortho- gonal with Z perpendicular to the rectified image planes and have their origin at the optical center of the left camera). Figure 1 illustrates their relationship. We assume a stereo vision system capable of generat- ing rectified stereo images, wherein the epipolar lines are parallel and horizontally aligned as if captured by paral- lel cameras. ...
Context 2
... object recognition was tested using four object classes derived from a foam barrier part be- ing inspected. The objective is to identify whether the barrier has been squeezed, stretched, or rotated, as shown in Figure 10. After training, 40 test objects (10 of each class) are tested. ...
Context 3
... training, 40 test objects (10 of each class) are tested. Figure 11 shows the classification results for each of these objects. All 40 objects are correctly identified to the appropriate classes. ...
Context 4
... 40 objects are correctly identified to the appropriate classes. Figure 11. 2D Classification Results. ...
Context 5
... object recognition was tested using the training set of Figure 12 on a set of 200 depth maps taken from different viewpoints of 3 different objects. The recognition rates of the experiment using Gaus- sian fuzzification, three training views, and the simple crisp-value inference method are shown in Table 1. ...
Similar publications
Food image recognition is one of the promising applications of visual object recognition in computer vision. In this study, a small-scale dataset consisting of 5822 images of ten categories and a five-layer CNN was constructed to recognize these images. The bag-of-features (BoF) model coupled with support vector machine was first tested as comparis...
Deep neural networks based methods have been proved to achieve outstanding performance on object detection and classification tasks. Despite significant performance improvement, due to the deep structures, they still require prohibitive runtime to process images and maintain the highest possible performance for real-time applications. Observing the...
In this contribution we present a method for object recognition in 2D scene. We use grammatical evolution to evolve a program to detect an object in scene and the second program which is responsible for recognition of detected object. We also describe developed software framework and we present some programs evolved by our system. Finally the perfo...
While recent deep neural networks have achieved a promising performance on object recognition, they rely implicitly on the visual contents of the whole image. In this paper, we train deep neural networks on the foreground (object) and background (context) regions of images respectively. Considering human recognition in the same situations, networks...
While recent deep neural network models have given promising performance on object recognition, they rely implicitly on the visual contents of the whole image. In this paper, we train deep neural networks on the foreground (object) and background (context) regions of images respectively. Considering human recognition in the same situations, network...
