I would like to add on to the post. Image processing is a field that has existed on its own longer than machine learning (ie, it predates machine learning decades before), its been taught mainly as a branch of engineering (electrical & electronics) & to some lesser degree also taught in computer science & physics' courses. Its only in the last decade or so, that image processing includes machine learning topics' for image recognition & understanding. The latest edition (3rd) has an added chapter on "Object Recognition" which wasn't available in the 1st & 2nd edition. The last time I passed through my local university bookstore (about a year ago), this textbook is stocked because its still currently a prescribed textbook for final year Electrical engineering courses.

We present a machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in real-time. Our algorithm typically produces files 2.5 times smaller than JPEG and JPEG 2000, 2 times smaller than WebP, and 1.7 times smaller than BPG on datasets of generic images across all quality levels. At the same time, our codec is designed to be lightweight and deployable: for example, it can encode or decode the Kodak dataset in around 10ms per image on GPU. Our architecture is an autoencoder featuring pyramidal analysis, an adaptive coding module, and regularization of the expected codelength. We also supplement our approach with adversarial training specialized towards use in a compression setting: this enables us to produce visually pleasing reconstructions for very low bitrates.

It is a key to construct a similarity graph in graph-oriented subspace learning and clustering. In a similarity graph, each vertex denotes a data point and the edge weight represents the similarity between two points. There are two popular schemes to construct a similarity graph, i.e., pairwise distance based scheme and linear representation based scheme. Most existing works have only involved one of the above schemes and suffered from some limitations. Specifically, pairwise distance based methods are sensitive to the noises and outliers compared with linear representation based methods. On the other hand, there is the possibility that linear representation based algorithms wrongly select inter-subspaces points to represent a point, which will degrade the performance. In this paper, we propose an algorithm, called Locally Linear Representation (LLR), which integrates pairwise distance with linear representation together to address the problems. The proposed algorithm can automatically encode each data point over a set of points that not only could denote the objective point with less residual error, but also are close to the point in Euclidean space. The experimental results show that our approach is promising in subspace learning and subspace clustering.

Learning with non-modular losses is an important problem when sets of predictions are made simultaneously. The main tools for constructing convex surrogate loss functions for set prediction are margin rescaling and slack rescaling. In this work, we show that these strategies lead to tight convex surrogates iff the underlying loss function is increasing in the number of incorrect predictions. However, gradient or cutting-plane computation for these functions is NP-hard for non-supermodular loss functions. We propose instead a novel surrogate loss function for submodular losses, the Lov\'asz hinge, which leads to O(p log p) complexity with O(p) oracle accesses to the loss function to compute a gradient or cutting-plane. We prove that the Lov\'asz hinge is convex and yields an extension. As a result, we have developed the first tractable convex surrogates in the literature for submodular losses. We demonstrate the utility of this novel convex surrogate through several set prediction tasks, including on the PASCAL VOC and Microsoft COCO datasets.

This is a curated list of medical data for machine learning. This list is provided for informational purposes only, please make sure you respect any and all usage restrictions for any of the data listed here. The National Library of Medicine presents MedPix Database of 53,000 medical images from 13,000 patients with annotations. These 1112 datasets are composed of structural and resting state functional MRI data along with an extensive array of phenotypic information. Also has clinical, genomic, and biomaker data. AMRG Cardiac Atlas The AMRG Cardiac MRI Atlas is a complete labelled MRI image set of a normal patient's heart acquired with the Auckland MRI Research Group's Siemens Avanto scanner.

The UK's National Health Service (NHS) and Intel are working together to make cancer detection more efficient through artificial intelligence. Last week, the University of Warwick, University Hospitals Coventry & Warwickshire NHS Trust (UHCW) alongside Intel said a new collaboration between the groups will push forward the classification of cancer cells "more efficiently and accurately through ground-breaking artificial intelligence." A team of scientists, hosted by the University of Warwick's Tissue Image Analytics (TIA) laboratory and led by Professor Nasir Rajpoot are currently creating a digital repository of known tumor and immune cells based on thousands of human tissue cells. This database of cancer information will then be used by algorithms to recognize these cells automatically. While some types of cancer are more aggressive than others, time is almost always an issue.

This paper addresses image classification through learning a compact and discriminative dictionary efficiently. Given a structured dictionary with each atom (columns in the dictionary matrix) related to some label, we propose cross-label suppression constraint to enlarge the difference among representations for different classes. Meanwhile, we introduce group regularization to enforce representations to preserve label properties of original samples, meaning the representations for the same class are encouraged to be similar. Upon the cross-label suppression, we don't resort to frequently-used $\ell_0$-norm or $\ell_1$-norm for coding, and obtain computational efficiency without losing the discriminative power for categorization. Moreover, two simple classification schemes are also developed to take full advantage of the learnt dictionary. Extensive experiments on six data sets including face recognition, object categorization, scene classification, texture recognition and sport action categorization are conducted, and the results show that the proposed approach can outperform lots of recently presented dictionary algorithms on both recognition accuracy and computational efficiency.

Cancer cells are to be detected and classified more efficiently and accurately, using ground-breaking artificial intelligence – thanks to a new collaboration between the University of Warwick, Intel Corporation, the Alan Turing Institute and University Hospitals Coventry & Warwickshire NHS Trust (UHCW). Scientists at the University of Warwick's Tissue Image Analytics (TIA) Laboratory--led by Professor Nasir Rajpoot from the Department of Computer Science--are creating a large, digital repository of a variety of tumour and immune cells found in thousands of human tissue samples, and are developing algorithms to recognize these cells automatically. "We are very excited about working with Intel under the auspices of the strategic relationship between Intel and the Alan Turing Institute," said Professor Rajpoot, who is also an Honorary Scientist at University Hospitals Coventry & Warwickshire NHS Trust (UHCW). "The collaboration will enable us to benefit from world-class computer science expertise at Intel with the aim of optimising our digital pathology image analysis software pipeline and deploying some of the latest cutting-edge technologies developed in our lab for computer-assisted diagnosis and grading of cancer." The digital pathology imaging solution aims to enable pathologists to increase their accuracy and reliability in analysing cancerous tissue specimens over what can be achieved with existing methods.

Editor's note: This is a followup to the recently published part 1. You may want to check it out before moving forward. In the last article we went through some basics of image-processing using OpenCV and basics of DICOM image. In this article we will talk about basics of deep learning from the lens of Convolutional Neural Nets. In the next article we will use Kaggle's lung cancer data-set, review the key items to look for in a lung cancer DICOM image and use Kera's to develop a model to predict lung cancer.

We present a conditional generative model to learn variation in cell and nuclear morphology and the location of subcellular structures from microscopy images. Our model generalizes to a wide range of subcellular localization and allows for a probabilistic interpretation of cell and nuclear morphology and structure localization from fluorescence images. We demonstrate the effectiveness of our approach by producing photo-realistic cell images using our generative model. The conditional nature of the model provides the ability to predict the localization of unobserved structures given cell and nuclear morphology.