Book ChapterDOI
Stacked Features Based CNN for Rotation Invariant Digit Classification
Ayushi Jain,Gorthi R. K. Sai Subrahmanyam,Deepak Mishra +2 more
- pp 527-533
Reads0
Chats0
TLDR
By using CNNs trained with prominent features of images, this work creates a stacked architecture which gives adequately satisfactory classification accuracy and demonstrates the architecture on handwritten digit classification and on the benchmark mnist-rot-12k.Abstract:
Covolutional neural networks extract deep features from input image. The features are invariant to small distortions in the input, but are sensitive to rotations, which makes them inefficient to classify rotated images. We propose an architecture that requires training with images having digits at one orientation, but is able to classify rotated digits oriented at any angle. Our network is built such that it uses any simple unit of CNN by training it with single orientation images and uses it multiple times in testing to accomplish rotation invariant classification. By using CNNs trained with prominent features of images, we create a stacked architecture which gives adequately satisfactory classification accuracy. We demonstrate the architecture on handwritten digit classification and on the benchmark mnist-rot-12k. The introduced method is capable of roughly identifying the orientation of digit in an image.read more
Citations
More filters
Journal Article
Rotation Invariant Face Detection Using Convolutional Neural Networks
TL;DR: The proposed networks have fewer free parameters and better generalization ability than the feedforward neural networks, and outperform the conventional convolutional neural networks.
Proceedings ArticleDOI
Scale and Rotation Corrected CNNs (SRC-CNNs) for Scale and Rotation Invariant Character Recognition: SRC-CNN for Scale and Rotation Invariant Character Recognition
TL;DR: It is demonstrated how the basic PCA based rotation and scale invariant image recognition can be integrated to CNN for achieving better rotational and scale invariances in classification.
Book ChapterDOI
Eigenvector Orientation Corrected LeNet for Digit Recognition
TL;DR: The approach ‘Eigenvector Orientation Corrected LeNet (EOCL)’ presents a simple method to make ordinary LeNet capable of detecting rotated digits, and also to predict the relative angle of orientation of digits with unknown orientation.
Proceedings ArticleDOI
Extracting Multi-Scale Rotation-Invariant Features in Convolution Neural Networks
TL;DR: In this article, a multi-scale rotation-invariant features were used in the convolutional neural network to identify rotational invariance of an object, which can successfully capture rotational features for various data sets.
References
More filters
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Proceedings Article
Spatial transformer networks
TL;DR: This work introduces a new learnable module, the Spatial Transformer, which explicitly allows the spatial manipulation of data within the network, and can be inserted into existing convolutional architectures, giving neural networks the ability to actively spatially transform feature maps.
Journal ArticleDOI
Image Super-Resolution Using Deep Convolutional Networks
TL;DR: Zhang et al. as discussed by the authors proposed a deep learning method for single image super-resolution (SR), which directly learns an end-to-end mapping between the low/high-resolution images.
Proceedings ArticleDOI
An empirical evaluation of deep architectures on problems with many factors of variation
TL;DR: A series of experiments indicate that these models with deep architectures show promise in solving harder learning problems that exhibit many factors of variation.
Journal ArticleDOI
Rotation-invariant convolutional neural networks for galaxy morphology prediction
TL;DR: A deep neural network model for galaxy morphology classification which exploits translational and rotational symmetry is developed in the context of the Galaxy Challenge, an international competition to build the best model for morphology classification based on annotated images from the Galaxy Zoo project.
Related Papers (5)
Learning rotation invariant convolutional filters for texture classification
Accelerating Image Classification using Feature Map Similarity in Convolutional Neural Networks
Keun-Young Park,Doo-Hyun Kim +1 more