Analysis of hierarchically-temporal dependencies for handwritten symbols and gestures recognition

Abstract

This work represents a biologically inspired approach to object recognition based on analysis of hierarchical and temporal data dependencies. The article describes the hierarchical temporal memory model (HTM) and its optimization for object recognition task. Optimization includes Gabor and Canny filter image preprocessing, which makes the model suitable for handwritten symbols and gestures recognition; using of additional clustering on the stage of spatial pooling, a new proposed temporal grouping algorithm increases the overall recognition accuracy of the model; a new genetic algorithm was designed for searching the optimal parameters of the model.

Application of Convolutional Neural Networks for Automatic Number Plate Recognition on Complex Background Images

“…• Absence of tolerance to geometric and local distortions in the image [5]. Therefore, convolutional neural networks (CNN) were selected for plate localization or finding and isolating the plate on the picture because they provide a partial invariance to image scales, displacements, rotations, different camera angles, and other input data distortions.…”

“…Hyperbolic tangent was chosen as the activation function (3); the functioning of neurons in a convolution layer was defined by (4); the functioning of neurons in a sub-sampling layer was defined by (5). For the CNN training, the resilient back-propagation algorithm (6) was used.…”

Detection of processing model basic elements in intellectual analysis of flexible processes through business process intelligence

“…Actually, each predicate assigns allowable relationships between the process operations. In case of hidden individual branches (predicates), for example, 2 R and R 5 , it is necessary to explicitly indicate that these predicates are removed from the model:…”

“…For example, event logs can record the performance of business processes, technological processes, user behavior in social networks. Process mining techniques are based on data mining that allows constructing a business process model with a rigid structure [2]. At the same time, a serious attention should be paid to flexible processes the structure of which can be changed both at configuration and performing stages.…”