G-Filter's Gaussianization Function for Interference Background

At present, image recognition processing technology has been playing a decisive role in the field of pattern recognition, of which automatic recognition of bank notes is an important research topic. Due to the limitation of the size of bill layout and printing method, many invoice layouts are not clear, skewed or distorted, and even there are irregular handwritten signature contents, which lead to the problem of recognition of digital characters on bill surface. In this regard, this paper proposes a data acquisition and recognition algorithm based on improved BP neural network for ticket number identification, which is based on the theory of image processing and recognition, combined with improved bill information recognition technology. First, in the pre-processing stage of bill image, denoising and graying of bill image are processed. After binarization of bill image, the tilt detection method based on Bresenham integer algorithm is used to correct the tilted bill image. Secondly, character localization and feature extraction are carried out for par characters, and the target background is separated from the interference background in order to extract the desired target characters. Finally, the improved BP neural network-based bill digit data acquisition and recognition algorithm is used to realize the classification and recognition of bill characters. The experimental results show that the improved method has better classification and recognition effect than other data acquisition and recognition algorithms.

Download Full-text

Gaussianization for Interference Background

International Journal of Computer Theory and Engineering ◽

10.7763/ijcte.2010.v2.195 ◽

2010 ◽

pp. 517-522 ◽

Cited By ~ 1

Author(s):

Wang Pingbo ◽

Suofu Tang ◽

Hongkai Wei ◽

Zhiming Cai

Keyword(s):

Interference Background

Download Full-text

Investigation of the Algorithm of Multipoint Target Detection over Structure-Like Interference Background

2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT) ◽

10.1109/usbereit48449.2020.9117666 ◽

2020 ◽

Author(s):

N.S. Vinogradova ◽

L.G. Dorosinsky

Keyword(s):

Target Detection ◽

Interference Background

Download Full-text

EXPRESS: Lending a Hand to Storytelling: Gesture’s Effects on Narrative Comprehension Moderated by Task Difficulty and Cognitive Ability

Quarterly Journal of Experimental Psychology ◽

10.1177/17470218211024913 ◽

2021 ◽

pp. 174702182110249

Author(s):

Nicola McKern ◽

Nicole Dargue ◽

Naomi Sweller ◽

Kazuki Sekine ◽

Elizabeth Austin

Keyword(s):

Cognitive Ability ◽

Verbal Memory ◽

Cognitive Abilities ◽

Background Noise ◽

Task Difficulty ◽

Intellectual Ability ◽

Narrative Comprehension ◽

Compelling Evidence ◽

Iconic Gesture ◽

Interference Background

Compelling evidence suggests observing iconic gestures benefits learning. While emerging evidence suggests typical iconic gestures benefit comprehension to a greater extent than atypical iconic gestures, it is unclear precisely when and for whom these gestures will be most helpful. The current study investigated factors that may moderate when and for whom gesture benefits narrative comprehension most, including the type of gesture, task difficulty, and individual differences in cognitive ability. Participants were shown a video narrative in which they observed either typical gestures (commonly produced gestures, highly semantically related to accompanying speech), atypical gestures (gestures that are seldom produced), or no gestures. The video narrative was either viewed with interference (background noise to increase task difficulty) or no interference (no background noise). To determine whether the effects of gesture observation and externally imposed task difficulty on narrative comprehension further depend on an individual’s cognitive abilities, participants completed four measures of cognitive abilities (immediate and delayed non-verbal memory, attention, and intellectual ability). Observing typical gestures significantly benefited narrative comprehension compared to atypical and no gestures combined, which did not differ significantly. Participants with below average and average levels of delayed non-verbal memory benefited more from typical gestures than atypical or no gestures compared to those with an above average level of delayed non-verbal memory. However, this interaction was only significant when the task was difficult (i.e., with interference) but not when the task was simple (i.e., no interference). This finding suggests that the type of iconic gesture observed may impact gesture’s beneficial effect on narrative comprehension, and that such gestures may be more beneficial in difficult tasks, but only for certain individuals.

Download Full-text