Natural image understanding using algorithm selection and high-level feedback

2013 ◽  
Author(s):  
Martin Lukac ◽  
Michitaka Kameyama ◽  
Kosuke Hiura
Keyword(s):  
Image Understanding ◽  
Natural Image ◽  
Algorithm Selection ◽  
High Level

scholarly journals Computer Vision

2021 ◽  
Vol 9 (VII) ◽  
pp. 1237-1239
Author(s):  
Omkar Madhukar Deshmukh
Keyword(s):  
Computer Vision ◽  
Sensory System ◽  
Image Understanding ◽  
Scientific Field ◽  
High Dimensional ◽  
Thought Processes ◽  
Knowledge Domain ◽  
Nursing Knowledge ◽  
Pure Mathematics ◽  
High Level

Computer vision may be a field of computer science that trains computers to interpret and perceive the visual world. exploitation digital pictures from cameras and videos and deep learning models, machines will accurately determine and classify objects — and so react to what they "see.”. Computer vision is Associate in Nursing knowledge domain scientific field that deals with however computers will gain high-level understanding from digital pictures or videos. From the angle of engineering, it seeks to grasp and alter tasks that the human sensory system will do. Computer vision tasks embrace strategies for exploit, processing, analyzing and understanding digital pictures, and extraction of high-dimensional knowledge from the important world so as to supply numerical or symbolic info, e.g. within the styles of selections. Understanding during this context suggests that the transformation of visual pictures (the input of the retina) into descriptions of the planet that be to thought processes and might elicit acceptable action. This image understanding will be seen because the disentangling of symbolic info from image knowledge mistreatment models created with the help of pure mathematics, physics, statistics, and learning theory.

scholarly journals Video Object Detection through Traditional and Deep Learning Methods

2020 ◽  
Vol 9 (4) ◽  
pp. 1822-1826
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Sparse Matrix ◽  
Image Understanding ◽  
Low Rank ◽  
Detection Methods ◽  
Video Object ◽  
Learning Methods ◽  
Primary Focus ◽  
High Level

Object detection in videos is gaining more attention recently as it is related to video analytics and facilitates image understanding and applicable to . The video object detection methods can be divided into traditional and deep learning based methods. Trajectory classification, low rank sparse matrix, background subtraction and object tracking are considered as traditional object detection methods as they primary focus is informative feature collection, region selection and classification. The deep learning methods are more popular now days as they facilitate high-level features and problem solving in object detection algorithms. We have discussed various object detection methods and challenges in this paper.

scholarly journals Automatic Segmentation of Nature Object Using Salient Edge Points Based Active Contour

2015 ◽  
Vol 2015 ◽  
pp. 1-12
Author(s):  
Shangbing Gao ◽  
Yunyang Yan ◽  
Youdong Zhang ◽  
Jingbo Zhou ◽  
Suqun Cao ◽  
...  
Keyword(s):  
Convex Hull ◽  
Active Contours ◽  
Object Segmentation ◽  
Image Understanding ◽  
Natural Images ◽  
Initial Contour ◽  
Natural Image ◽  
Salient Object ◽  
Edge Preserving ◽  
Edge Points

Natural image segmentation is often a crucial first step for high-level image understanding, significantly reducing the complexity of content analysis of images. LRAC may have some disadvantages. (1) Segmentation results heavily depend on the initial contour selection which is a very skillful task. (2) In some situations, manual interactions are infeasible. To overcome these shortcomings, we propose a novel model for unsupervised segmentation of viewer’s attention object from natural images based on localizing region-based active model (LRAC). With aid of the color boosting Harris detector and the core saliency map, we get the salient object edge points. Then, these points are employed as the seeds of initial convex hull. Finally, this convex hull is improved by the edge-preserving filter to generate the initial contour for our automatic object segmentation system. In contrast with localizing region-based active contours that require considerable user interaction, the proposed method does not require it; that is, the segmentation task is fulfilled in a fully automatic manner. Extensive experiments results on a large variety of natural images demonstrate that our algorithm consistently outperforms the popular existing salient object segmentation methods, yielding higher precision and better recall rates. Our framework can reliably and automatically extract the object contour from the complex background.

Situated Image Understanding in a Multiagent Framework

1998 ◽  
Vol 12 (05) ◽  
pp. 595-624 ◽  
Author(s):  
N. Bianchi ◽  
P. Bottoni ◽  
P. Mussio ◽  
C. Spinu ◽  
C. Garbay
Keyword(s):  
Liver Biopsy ◽  
Image Understanding ◽  
The State ◽  
Reactive Control ◽  
Preliminary Results ◽  
Low Level ◽  
Local Properties ◽  
High Level ◽  
Biopsy Image

The paper addresses the problem of controlling situated image understanding processes. Two complementary control styles are considered and applied cooperatively, a deliberative one and a reactive one. The role of deliberative control is to account for the unpredictability of situations, by dynamically determining which strategies to pursue, based on the results obtained so far and more generally on the state of the understanding process. The role of reactive control is to account for the variability of local properties of the image by tuning operations to subimages, each one being homogeneous with respect to a given operation. A variable organization of agents is studied to face this variability. The two control modes are integrated into a unified formalism describing segmentation and interpretation activities. A feedback from high level interpretation tasks to low level segmentation tasks thus becomes possible and is exploited to recover wrong segmentations. Preliminary results in the field of liver biopsy image understanding are shown to demonstrate the potential of the approach.

scholarly journals MODELING SELECTIVE PERCEPTION OF COMPLEX, NATURAL SCENES

2005 ◽  
Vol 14 (01n02) ◽  
pp. 233-260 ◽  
Author(s):  
ROXANNE CANOSA
Keyword(s):  
Image Understanding ◽  
Natural Scenes ◽  
Topographic Map ◽  
Biologically Inspired ◽  
Selective Perception ◽  
Scene Representation ◽  
Level Information ◽  
Fixation Locations ◽  
Ground Segmentation ◽  
High Level

Computational modeling of the human visual system is of current interest to developers of artificial vision systems, primarily because a biologically-inspired model can offer solutions to otherwise intractable image understanding problems. The purpose of this study is to present a biologically-inspired model of selective perception that augments a stimulus-driven approach with a high-level algorithm that takes into account particularly informative regions in the scene. The representation is compact and given in the form of a topographic map of relative perceptual conspicuity values. Other recent attempts at compact scene representation consider only low-level information that codes salient features such as color, edge, and luminance values. The previous attempts do not correlate well with subjects' fixation locations during viewing of complex images or natural scenes. This study uses high-level information in the form of figure/ground segmentation, potential object detection, and task-specific location bias. The results correlate well with the fixation densities of human viewers of natural scenes, and can be used as a preprocessing module for image understanding or intelligent surveillance applications.

scholarly journals Towards improving edge quality using combinatorial optimization and a novel skeletonize algorithm

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Marvin Arnold ◽  
Stefanie Speidel ◽  
Georges Hattab
Keyword(s):  
Optimal Parameter ◽  
Parameter Tuning ◽  
Natural Image ◽  
Data Sets ◽  
Post Processing ◽  
Algorithm Selection ◽  
Object Boundary ◽  
Discrete Parameter ◽  
Extensive Evaluation ◽  
Edge Quality

Abstract Background Object detection and image segmentation of regions of interest provide the foundation for numerous pipelines across disciplines. Robust and accurate computer vision methods are needed to properly solve image-based tasks. Multiple algorithms have been developed to solely detect edges in images. Constrained to the problem of creating a thin, one-pixel wide, edge from a predicted object boundary, we require an algorithm that removes pixels while preserving the topology. Thanks to skeletonize algorithms, an object boundary is transformed into an edge; contrasting uncertainty with exact positions. Methods To extract edges from boundaries generated from different algorithms, we present a computational pipeline that relies on: a novel skeletonize algorithm, a non-exhaustive discrete parameter search to find the optimal parameter combination of a specific post-processing pipeline, and an extensive evaluation using three data sets from the medical and natural image domains (kidney boundaries, NYU-Depth V2, BSDS 500). While the skeletonize algorithm was compared to classical topological skeletons, the validity of our post-processing algorithm was evaluated by integrating the original post-processing methods from six different works. Results Using the state of the art metrics, precision and recall based Signed Distance Error (SDE) and the Intersection over Union bounding box (IOU-box), our results indicate that the SDE metric for these edges is improved up to 2.3 times. Conclusions Our work provides guidance for parameter tuning and algorithm selection in the post-processing of predicted object boundaries.

Sign in / Sign up

Export Citation Format

Share Document