Feature extraction from photographical images using a hybrid neural network

被引：5

作者：

Becanovic, V ^{[1
]}

Kermit, M ^{[1
]}

Eide, ÅJ ^{[1
]}

机构：

[1] KTH, Dept Phys, SE-10405 Stockholm, Sweden

来源：

NINTH WORKSHOP ON VIRTUAL INTELLIGENCE/DYNAMIC NEURAL NETWORKS: ACADEMIC/INDUSTRIAL/NASA/DEFENSE TECHNICAL INTERCHANGE AND TUTORIALS | 1999年 / 3728卷

关键词：

object recognition; saccadic eye movement; foveation; neural network; PCNN; SOM; license plate recognition; probability surface; segmentation; time-series;

D O I：

10.1117/12.343053

中图分类号：

V [航空、航天];

学科分类号：

08 ; 0825 ;

摘要：

A new method for extracting features from photographic images has been developed. The input image is through a pulse coupled neural network (PCNN) transformed to a set of signatures, well suited for classification by unsupervised neural networks. A strategy using multiple self-organising feature maps (SORI) in a hierarchical manner is developed. With this approach, using a certain degree of supervision, an acceptable classification is obtained when applied to test images. The method is applied to license plate recognition.

引用

页码：351 / 361

页数：11

共 19 条

[1]

[Anonymous], 1998, IMAGE PROCESSING USI

[2]

BONMASSAR G, 1994, ICPR P, V12, P204

[3] The local structure of space-variant images [J].

Fischl, B ;

Cohen, MA ;

Schwartz, EL .

NEURAL NETWORKS, 1997, 10 (05) :815-831

[4]

Ganong WF., 1985, REV MED PHYSL, V12th

[5] PARALLEL AND DETERMINISTIC ALGORITHMS FROM MRFS - SURFACE RECONSTRUCTION [J].

GEIGER, D ;

GIROSI, F .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1991, 13 (05) :401-412

[6]

GERNAN S, 1984, T IEEE PATTERN ANAL, V6, P721

[7]

Gonzales R.C., 1992, DIGITAL IMAGE PROCES

[8]

Hall D. L., 1992, MATH TECHNIQUES MULT

[9]

Haykin S., 1994, NEURAL NETWORKS COMP

[10]

HORN D, 1997, NEURAL COMPUTATI NOV, V9

← 1 2 →