Bilateral Filter Evaluation Based on Exponential Kernels

in Pattern Recognition (ICPR), 2012 21st International Conference on (2012)

The well-known bilateral filter is used to smooth noisy images while keeping their edges. This filter is commonly used with Gaussian kernel functions without real justification. The choice of the kernel ... [more ▼]

The well-known bilateral filter is used to smooth noisy images while keeping their edges. This filter is commonly used with Gaussian kernel functions without real justification. The choice of the kernel functions has a major effect on the filter behavior. We propose to use exponential kernels with L1 distances instead of Gaussian ones. We derive Stein's Unbiased Risk Estimate to find the optimal parameters of the new filter and compare its performance with the conventional one. We show that this new choice of the kernels has a comparable smoothing effect but with sharper edges due to the faster, smoothly decaying kernels. [less ▲]

A New Multi-Lateral Filter for Real-Time Depth Enhancement

in 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance (2011)

A New 1-D Colour Model and its Application to Image Filtering

in 2011 7th International Symposium on Image and Signal Processing and Analysis (ISPA) (2011)

Mahalanobis-based Adaptive Nonlinear Dimension Reduction

in 20th International Conference on Pattern Recognition (2010)

Meaningful 3D shape partitioning using Morse functions

in 2009 16th IEEE International Conference on Image Processing (2009)

3D Object Recognition Using Fully Intrinsic Skeletal Graphs

in International Conference on Computational Imaging, 2008 (2008, February)

3D Mixed Invariant and its Application on Object Classification

in IEEE International Conference on Acoustics, Speech and Signal Processing, 2007. ICASSP 2007 (2007, April)

Industrial defect detection on the edge with deep learning over scarcely labeled and extremely imbalanced data

E-print/Working paper (n.d.)

Abstract—Reliable automated defect detection is an integral part of modern manufacturing and improved performance can provide a competitive advantage. Despite the proven capabilities of convolutional ... [more ▼]

Abstract—Reliable automated defect detection is an integral part of modern manufacturing and improved performance can provide a competitive advantage. Despite the proven capabilities of convolutional neural networks (CNNs) for image classification, application on real world tasks remains challenging due to the high demand for labeled and well balanced data of the common supervised learning scheme. Semi-supervised learning (SSL) promises to achieve comparable accuracy while only requiring a small fraction of the training samples to be labeled. However, SSL methods struggle with data imbalance and existing benchmarks do not reflect the challenges of real world applications. In this work we present a CNN-based defect detection unit for thermal sensors. We describe how to collect data from a running process and release our dataset of 1k labeled and 293k unlabeled samples. Furthermore, we investigate the use of SSL under this challenging real world task. [less ▲]