Wavelet-Based Feature Extraction for Handwritten Numerals

Romero, Diego J.; Ruedin, Ana M. C.; Seijas, Leticia M.

doi:10.1007/978-3-642-04146-4_41

Cited by 5 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When scaled, its essential support is a disk with radius proportional to the scale. If σ ≠1, we have the anisotropic Mexican hat, stretched out or shortened, and its support is an ellipse [17]. The frequency domain response of Mexican hat wavelet is given by…”

Section: A 2-d Continuous Wavelet Transformmentioning

confidence: 99%

Automatic Image Registration Using Mexican Hat Wavelet, Invariant Moment, and Radon Transform

Sarvaiya¹,

Patnaik²

2011

SpecialIssue

View full text Add to dashboard Cite

Abstract-Image registration is an important and fundamental task in image processing used to match two different images. Given two or more different images to be registered, image registration estimates the parameters of the geometrical transformation model that maps the sensed images back to its reference image. A feature-based approach to automated imageto-image registration is presented. The characteristic of this approach is that it combines Mexican-Hat Wavelet, Invariant Moments and Radon Transform. Feature Points from both images are extracted using Mexican-Hat Wavelet and controlpoint correspondence is achieved with invariant moments. After detecting corresponding control points from reference and sensed images, to recover scaling and rotation a line and triangle is form in both images respectively and applied radon transform to register images.

show abstract

Section: A 2-d Continuous Wavelet Transformmentioning

confidence: 99%

Automatic Image Registration Using Mexican Hat Wavelet, Invariant Moment, and Radon Transform

Sarvaiya¹,

Patnaik²

2011

SpecialIssue

View full text Add to dashboard Cite

show abstract

“…Flourished deep learning methods, especially convolutional neural networks (CNNs) ( Lecun et al, 1998 ), could adaptively extract features from diversified datasets. Also, they have been proven more potent than classic computer vision algorithms like wavelet transforms ( Romero et al, 2009 ) and Radon transforms ( Aradhya et al, 2007 ) on a famous grayscale dataset MNIST, even without supervising ( Ji et al, 2019 ). Therefore, we attempt to adopt CNNs to achieve end-to-end feature extractions of animal behaviors that are comprehensive and discriminative.…”

Section: Introductionmentioning

confidence: 99%

Selfee, self-supervised features extraction of animal behaviors

Jia

Guo

et al. 2022

eLife

View full text Add to dashboard Cite

Fast and accurately characterizing animal behaviors is crucial for neuroscience research. Deep learning models are efficiently used in laboratories for behavior analysis. However, it has not been achieved to use an end-to-end unsupervised neural network to extract comprehensive and discriminative features directly from social behavior video frames for annotation and analysis purposes. Here, we report a self-supervised feature extraction (Selfee) convolutional neural network with multiple downstream applications to process video frames of animal behavior in an end-to-end way. Visualization and classification of the extracted features (Meta-representations) validate that Selfee processes animal behaviors in a way similar to human perception. We demonstrate that Meta-representations can be efficiently used to detect anomalous behaviors that are indiscernible to human observation and hint in-depth analysis. Furthermore, time-series analyses of Meta-representations reveal the temporal dynamics of animal behaviors. In conclusion, we present a self-supervised learning approach to extract comprehensive and discriminative features directly from raw video recordings of animal behaviors and demonstrate its potential usage for various downstream applications.

show abstract

“…Ebrahimzadeh and Jampour [6] presented an approach using Histogram of Oriented Gradients and linear SVM for handwritten digit recognition. Romero et al [7] introduced a technique based on Wavelet transform and ANN for handwritten numerals recognition. A comparison between DCT and Discrete Wavelet Transform (DWT) to capture features of Arabic handwritten characters without overlapping characters has been introduced by Lawgali et al [8].…”

Section: Figure 1 Different Samples Images Of Handwritten Digitsmentioning

confidence: 99%