Construction of efficient detectors for character information recognition

Telnykh, Alexander; Nuidel, I. V.; Samorodova, Yulia

doi:10.1016/j.procs.2020.02.170

Cited by 4 publications

(6 citation statements)

References 20 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An intelligent artificial cognitive system was developed back in 2015 [1]. This system performs intellectual image analysis in accordance with a given semantic dictionary (for example, recognition of symbolic information) [56][57][58]. In the course of the development of an artificial cognitive system for content-based image analysis, a biomorphic model for the construction and interaction of structural and functional modules of living systems during visual signal processing was constructed.…”

Section: The System Of Content-based Image Retrieval-a Biomorphic Str...mentioning

confidence: 99%

“…The system of content-based image retrieval is organized as follows. Each concept of the dictionary corresponds to a cascade detector [59], sticking to strong classifiers based on nonlocal binary patterns [56]. The object properties are determined by an attribute detector also based on nonlocal binary patterns (Figure 5).…”

Section: System Of Content-based Image Retrieval: General Descriptionmentioning

confidence: 99%

“…The specified objects in the image can be detected and recognized, using the approach proposed by Viola and Jones [59]. For developing efficient detectors, we make use of a modified census transform [56] for a rectangle of any size within the detection region.…”

Section: System Of Content-based Image Retrieval: Algorithmsmentioning

confidence: 99%

“…The detector is a cascade of strong classifiers connected in series (Figure 9). One of the tasks of improving the recognition system is the search for effective detectors, in which the IAP RAS team is involved [56]. The results of a computational experiment on the recognition of the numbers on the railway carriage or tank cars are presented [56].…”

Section: Strong Classifiermentioning

confidence: 99%

“…One of the tasks of improving the recognition system is the search for effective detectors, in which the IAP RAS team is involved [56]. The results of a computational experiment on the recognition of the numbers on the railway carriage or tank cars are presented [56]. To detect the number, a database of images of the trains passing near a video camera installed at the railway station was collected.…”

Section: Strong Classifiermentioning

confidence: 99%

See 4 more Smart Citations

A Biomorphic Model of Cortical Column for Content—Based Image Retrieval

Telnykh

Nuidel

Shemagina

et al. 2021

Entropy

Self Cite

View full text Add to dashboard Cite

How do living systems process information? The search for an answer to this question is ongoing. We have developed an intelligent video analytics system. The process of the formation of detectors for content-based image retrieval aimed at detecting objects of various types simulates the operation of the structural and functional modules for image processing in living systems. The process of detector construction is, in fact, a model of the formation (or activation) of connections in the cortical column (structural and functional unit of information processing in the human and animal brain). The process of content-based image retrieval, that is, the detection of various types of images in the developed system, reproduces the process of “triggering” a model biomorphic column, i.e., a detector in which connections are formed during the learning process. The recognition process is a reaction of the receptive field of the column to the activation by a given signal. Since the learning process of the detector can be visualized, it is possible to see how a column (a detector of specific stimuli) is formed: a face, a digit, a number, etc. The created artificial cognitive system is a biomorphic model of the recognition column of living systems.

show abstract

Section: The System Of Content-based Image Retrieval-a Biomorphic Str...mentioning

confidence: 99%

Section: System Of Content-based Image Retrieval: General Descriptionmentioning

confidence: 99%