The Review of Spatial Objects Recognition Models and Algorithms

Andrianov, D.E.; Еремеев, С. В.; Kuptsov, Kirill

doi:10.1016/j.proeng.2015.12.126

Cited by 4 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Viewpoint & Geometry + - The problem of spatial object recognition in geographicalinformation systems is tackled by means of reviewingmethods in which it can be made easier as well as moreefficient. They are done in the following steps: by improvingthe quality of object recognition, by creating general rules toreduce the possibility of erratical classification of objects intoclasses and by establishing rules defining the correlation ofspatial objects of different classes [5] . Object recognition firsttakes place on the topological basis, wherein, objects in animage are classified into categories on the basis of imagesegmentation, and the various measures which can then beextracted by such measures.…”

Section: Various Object Recognition Techniquesmentioning

confidence: 99%

Efficient Object Recognition using Convolution Neural Networks Theorem

Thakral¹,

Shekhar²,

Victor³

2017

IJCA

View full text Add to dashboard Cite

Object recognition is the process of identification of an object in an image. There exist various algorithms for the same. Appearance based algorithms have demonstrated good efficiency, however, their performance gets affected adversely in the presence of clutter or when background changes are affected. We hope to overcome this issue by using Convolution Neural Network (CNN) Theorem. The approach is shape based and has been proven to work well under broad range of circumstances: varied lighting conditions, affine transformations, etc. It involves tiling, which is the phenomenon of the use of multiple layers of neurons to process small portions of the image, which are then used to obtain better representations of the image. This allows CNN to be translation-tolerant. The neural elements learn to recognize objects about which they have no previous information, this "learning" mechanism is affected by the fact that representations of the image are learned by the inner layers of the deep architectures of neurons. Unlike RBM and Auto-encoder, which are capable of learning only single global weight matrix layers, the CNN theorem makes use of shared weight in convolution layers, which means that the same filter (weight bank) is used for each pixel in the layer, which reduces the memory footprint and improves performance.

show abstract

Section: Various Object Recognition Techniquesmentioning

confidence: 99%