ILBPSDNet: Based on improved local binary pattern shallow deep convolutional neural network for character recognition

Abstract

This paper proposes an architecture based on the improved local binary pattern (LBP) shallow deep convolution neural network, which integrates hand-crafted feature preprocessing and the advantage of character learning in the supervised high-level function of CNN, in order to enhance its performance. This study introduced the information of scale space into the LBP to reduce the sensitivity to noise, and applied feature maps with two features, the maximum selection feature map (MLBP) and the first selection feature map (FLBP). The former selected the edge with the strongest intensity to reduce the influence of noise points, while the latter measured local binary features through the scale detection of an effective edge. In the network architecture design, according to the differences of input features, networks of different depths were used for learning, and the features learned by the two networks were adopted for classification. The experimental results show that, the ILBPSDNet proposed had certain recognition abilities in many character data sets, and the network parameters and computation were also reduced. Therefore, it has a significant effect in realizing the application of real-time character recognition. Finally, compared with other latest networks, its network performance could be maintained at a certain level.

Step-by-Step: Learning Japanese Writing on Android for Beginners

“…LBP was chosen as the pattern recognition method to be evaluated in this study for its effectiveness in identifying character writing by users [6], [9], [19], [20].…”

Telugu letters dataset and parallel deep convolutional neural network with a SGD optimizer model for TCR

“…The current standard in computer vision (CV) is DCNNs. CNNs consistently place first in object recognition competitions and have been used for various visual tasks, including pose estimation, segmentation, object detection and localization, and visual saliency [25]. CNNs are a basis that may be used to instantiate numerous designs rather than a single design, which makes them less than ideal as a cognitive architecture.…”

Design of Quick Search Method for Key Feature Images in Mobile Networks

“…In the mobile network, the expression defects of image texture features will also affect the transmission of image data [12,13]. The 3 × 3 neighborhood of the basic local binary mode is extended to any neighborhood,, that is, the computation of local binary pattern features is no longer limited to 3 × 3 neighborhood, but select a circular neighborhood with a center point as the center and a radius of R [14,15]. P points are sampled at equal intervals around the circle and the binarization processing is performed by comparing the gray values of these points and the center point.…”