IMAGE RECOGNITION BY INTEGRATION OF CONNECTIONIST AND SYMBOLIC APPROACHES

Author(s):  
F. ROLI ◽  
S. B. SERPICO ◽  
G. VERNAZZA

This paper presents a methodology for integrating connectionist and symbolic approaches to 2D image recognition. The proposed integration paradigm exploits the synergy of the two approaches for both the training and the recognition phases of an image recognition system. In the training phase, a symbolic module provides an approximate solution to a given image-recognition problem in terms of symbolic models. Such models are hierarchically organized into different abstraction levels, and include contextual descriptions. After mapping such models into a complex neural architecture, a neural training process is carried out to optimize the solution of the recognition problem. The so-obtained neural networks are used during the recognition phase for pattern classification. In this phase, the role of symbolic modules consists of managing complex aspects of information processing: abstraction levels, contextual information, and global recognition hypotheses. A hybrid system implementing the proposed integration paradigm is presented, and its advantages over single approaches are assessed. Results on Magnetic Resonance image recognition are reported, and comparisons with some well-known classifiers are made.

1998 ◽  
Vol 11 (1) ◽  
pp. 113-116
Author(s):  
V. Rucco ◽  
P.-T. Basadonna ◽  
D. Gasparini

We describe a case of low back pain (LBP) secondary to a facet syndrome, with a magnetic resonance image of enlarged zygapophyseal inclusions, which both regressed with manipulative therapy. The role of the lumbar zygapophyseal inclusion in the pain syndrome remains uncertain, because there are no studies on these inclusions in the lumbar facet syndrome. The explanation of the role of manual therapy is also uncertain (adjusting joint subluxations, restoring bony alignment, reducing nuclear protrusion, reducing meniscoid entrapment or extrapment, decompressing facet joints, etc). The diagnosis of classical facet syndrome LBP was made by history-taking and physical examination. The diagnosis of intra-articular enlargements was made by magnetic resonance imaging. The manipulative therapy consisted of manipulations in rotation with the spine placed in kyphosis. Before every manipulation session, spontaneous pain, pain with pressure on the zygapophyseal joint and the range of thoracic and lumbar spine motions were evaluated. After the fourth manipulation session, the patient's pain was alleviated and the enlarged zygapophyseal inclusions were no longer visible. The clinical improvement continued at the controls one and two months after the end of the manipulative therapy. This is the first report of facet syndrome LBP with a magnetic resonance image of enlarged zygapophyseal inclusions which both regressed with manipulative therapy. It is interesting to speculate on the possible mechanisms to explain this outcome, but further studies are needed.


2014 ◽  
Vol 543-547 ◽  
pp. 2209-2212
Author(s):  
Chun Hua Xiong ◽  
You Jie Zhou ◽  
Gao Jun An ◽  
Chang Bo Lu

Based on the existing contour tracing image recognition technology, combining the embedded system technology and the computer storage control technology, the author makes an integrated design, adopts the image processing chip, USB controller, the imaging sensor and other hardware circuits and develops an intelligent image system. The system can make real-time monitoring the size and change of millimeter-sized irregular target objects. Its applicable value in the fields such as intelligent monitoring of oil equipment, medical imaging and criminal investigation is very high.


Perception ◽  
10.1068/p5192 ◽  
2005 ◽  
Vol 34 (9) ◽  
pp. 1117-1134 ◽  
Author(s):  
Claus-Christian Carbon ◽  
Helmut Leder

We investigated the early stages of face recognition and the role of featural and holistic face information. We exploited the fact that, on inversion, the alienating disorientation of the eyes and mouth in thatcherised faces is hardly detectable. This effect allows featural and holistic information to be dissociated and was used to test specific face-processing hypotheses. In inverted thatcherised faces, the cardinal features are already correctly oriented, whereas in undistorted faces, the whole Gestalt is coherent but all information is disoriented. Experiment 1 and experiment 3 revealed that, for inverted faces, featural information processing precedes holistic information. Moreover, the processing of contextual information is necessary to process local featural information within a short presentation time (26 ms). Furthermore, for upright faces, holistic information seems to be available faster than for inverted faces (experiment 2). These differences in processing inverted and upright faces presumably cause the differential importance of featural and holistic information for inverted and upright faces.


Sign in / Sign up

Export Citation Format

Share Document