2017 · 23 citations · 10 references
ComputingBiomedical EngineeringComputer ScienceBiomedical ImagingComputer VisionMachine LearningData CompressionDigital Image ProcessingImage CompressionImage ProcessingLossy Data CompressionPattern RecognitionAutomatic ClassificationBiomedical ApplicationsClassification AccuracyClassification Accuracy AssessmentCompressionCompression RatioConvolutional Neural NetworksDeep Learning-based Classification
In many biomedical applications, images are stored and transmitted in the form of compressed images. However, typical pattern classifiers are trained using original images. There has been little prior study on how lossily decompressed images would impact the classification performance. In a case study of automatic classification of malaria infected cells, we used decompressed cell images as the inputs to deep convolutional neural networks. We evaluated how various lossy image compression methods and varying compression ratios would impact the classification accuracies. Specifically, we compared four compression methods: lossy compression via bitplane reduction, JPEG and JPEG 2000, and sparse autoencoders. Decompressed images were fed into LeNet-5 for training and testing. Simulation results showed that for similar compression ratios, the bitplane reduction method had the lowest classification accuracy, while JPEG and JPEG 2000 methods could maintain good accuracies. In particular, JPEG 2000 decompressed images could achieve about 95% accuracy even after 30 to 1 compression. We also provide classification results based on the widely used MNIST dataset, where handwritten digits were found to be much easier to classify using decompressed images, with about 90% accuracy still achievable using only one single bitplane. As a lossy compression method, Autoencoder was also applied to the MNIST dataset, achieving about 85% accuracy with a compression ratio much higher than the other three lossy image compression methods. Autoencoders were also found to provide more scalable compression ratios, while capable of maintaining good classification accuracies.
10
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
A Fast Learning Algorithm for Deep Belief Nets
Geoffrey E. Hinton, Simon Osindero, Yee‐Whye Teh · Neural Computation · 2006 · 16.4K citations
Why Does Unsupervised Pre-training Help Deep Learning?
Dumitru Erhan, Aaron Courville, Yoshua Bengio et al. · 2010 · 2.1K citations
High performance scalable image compression with EBCOT
David Taubman · IEEE Transactions on Image Processing · 2000 · 1.9K citations