Image processing chip for small object detection

A new, front-end image processing chip is presented for real-time small object detection. It has been implemented using a 0.6 µ, 3.3 V CMOS technology and operates on 10-bit input data at 54 megasamples per second. It occupies an area of 12.9 mm×13.6 mm (including pads), dissipates 1.5 W, has 92 I/O pins and is to be housed in a 160-pin ceramic quarter flat-pack. It performs both one- and two-dimensional FIR filtering and a multilayer perceptron (MLP) neural network function using a reconfigurable array of 21 multiplication-accumulation cells which corresponds to a window size of 7×3. The chip can cope with images of 2047 pixels per line and can be cascaded to cope with larger window sizes. The chip performs two billion fixed point multiplications and additions per second.

Detection of changes of the optic disc in glaucomatous eyes:Clinical examination and image analysis with the Topcon Imagenet system

Purpose: This study was designed to evaluate the clinical agreement in the detection of optic disc changes and the ability of computerized image analysis to detect glaucomatous deterioration of the optic disc. Methods: Pairs of stereophotographs of 35 glaucomatous optic discs taken 5 years apart and of 5 glaucomatous discs photographed twice on the same day. Two glaucoma specialists examined the pairs of stereophotographs (35 cases and 5 controls) in a masked manner and judged whether the optic disc showed changes in the optic disc compatible with progression of glaucomatous damage. The stereophotographs of the five optic discs photographed twice on the same day (which by definition did not change) and of five cases judged to have deteriorated by both glaucoma specialists were analyzed by computerized image analysis with the Topcon ImageNet system. Intra- and inter-observer agreement in the detection of optic disc changes (evaluated using kappa statistic), and changes in the rim area to disc area ratio (evaluated using descriptive statistics and paired t-test). Results: Intra-observer agreement had a kappa value of 0.75 for observer 1 and 0.60 for the observer 2. Inter-observer agreement between the glaucoma specialists had a kappa value of 0.60. The image analyzer did not discriminate between controls and cases with clinically apparent glaucomatous change of the optic disc. Conclusion: Clinical agreement in detecting changes in the optic disc was moderate to substantial. Computerized image analysis with the Topcon ImageNet system appeared not to be useful in detecting glaucomatous changes of the optic disc.

Whole Slide Image Cytometry: a Novel Method for the Detection and Quantification of Abnormal DNA Contents in Barrett’s Oesophagus

Background: Barrett's oesophagus (BO) is a well recognized precursor of the majority of cases of oesophageal adenocarcinoma (OAC). Endoscopic surveillance of BO patients is frequently undertaken in an attempt to detect early OAC, high grade dysplasia (HGD) or low grade dysplasia (LGD). However histological interpretation and grading of dysplasia is subjective and poorly reproducible. The alternative flow cytometry and cytology-preparation image cytometry techniques require large amounts of tissue and specialist expertise which are not widely available for frontline health care.
Methods: This study has combined whole slide imaging with DNA image cytometry, to provide a novel method for the detection and quantification of abnormal DNA contents. 20 cases were evaluated, including 8 Barrett's specialised intestinal metaplasia (SIM), 6 LGD and 6 HGD. Feulgen stained oesophageal sections (1µm thickness) were digitally scanned in their entirety and evaluated to select regions of interests and abnormalities. Barrett’s mucosa was then interactively chosen for automatic nuclei segmentation where irrelevant cell types are ignored. The combined DNA content histogram for all selected image regions was then obtained. In addition, histogram measurements, including 5c exceeding ratio (xER-5C), 2c deviation index (2cDI) and DNA grade of malignancy (DNA-MG), were computed.
Results: The histogram measurements, xER-5C, 2cDI and DNA-MG, were shown to be effective in differentiating SIM from HGD, SIM from LGD, and LGD from HGD. All three measurements discriminated SIM from HGD cases successfully with statistical significance (pxER-5C=0.0041, p2cDI=0.0151 and pDNA-MG=0.0057). Statistical significance is also achieved differentiating SIM from LGD samples with pxER-5C=0.0019, p2cDI=0.0023 and pDNA-MG=0.0030. Furthermore the differences between LGD and HGD cases are statistical significant (pxER-5C=0.0289, p2cDI=0.0486 and pDNA-MG=0.0384).
Conclusion: Whole slide image cytometry is a novel and effective method for the detection and quantification of abnormal DNA content in BO. Compared to manual histological review, this proposed method is more objective and reproducible. Compared to flow cytometry and cytology-preparation image cytometry, the current method is low cost, simple to use and only requires a single 1µm tissue section. Whole slide image cytometry could assist the routine clinical diagnosis of dysplasia in BO, which is relevant for future progression risk to OAC.

Fast Retinal Vessel Detection and Measurement Using Wavelets and Edge Location Refinement

The relationship between changes in retinal vessel morphology and the onset and progression of diseases such as diabetes, hypertension and retinopathy of prematurity (ROP) has been the subject of several large scale clinical studies. However, the difficulty of quantifying changes in retinal vessels in a sufficiently fast, accurate and repeatable manner has restricted the application of the insights gleaned from these studies to clinical practice. This paper presents a novel algorithm for the efficient detection and measurement of retinal vessels, which is general enough that it can be applied to both low and high resolution fundus photographs and fluorescein angiograms upon the adjustment of only a few intuitive parameters. Firstly, we describe the simple vessel segmentation strategy, formulated in the language of wavelets, that is used for fast vessel detection. When validated using a publicly available database of retinal images, this segmentation achieves a true positive rate of 70.27%, false positive rate of 2.83%, and accuracy score of 0.9371. Vessel edges are then more precisely localised using image profiles computed perpendicularly across a spline fit of each detected vessel centreline, so that both local and global changes in vessel diameter can be readily quantified. Using a second image database, we show that the diameters output by our algorithm display good agreement with the manual measurements made by three independent observers. We conclude that the improved speed and generality offered by our algorithm are achieved without sacrificing accuracy. The algorithm is implemented in MATLAB along with a graphical user interface, and we have made the source code freely available. 

Automatic detection and classification of football players

Color segmentation of images usually requires a manual selection and classification of samples to train the system. This paper presents an automatic system that performs these tasks without the need of a long training, providing a useful tool to detect and identify figures. In real situations, it is necessary to repeat the training process if light conditions change, or if, in the same scenario, the colors of the figures and the background may have changed, being useful a fast training method. A direct application of this method is the detection and identification of football players.

Terahertz detection of illegal objects

This paper describes the main parameters - contrast, spatial resolution, and thermal sensitivity - which define the performance of any stand-off imaging system. The origin of the signature for both metal and dielectric objects hidden under clothing in the frequency range from 100 GHz to 500 GHz is discussed. At 100 GHz the signature is dominated by reflection whilst at 500 GHz it is dominated by emission. A 94-GHz-passive millimetre-wave imaging system has been designed and fabricated to image objects under clothing. This imager is based on a Schmidt camera folded using polarisation techniques.

Programmable image processing chip

A new high performance, programmable image processing chip targeted at video and HDTV applications is described. This was initially developed for image small object recognition but has much broader functional application including 1D and 2D FIR filtering as well as neural network computation. The core of the circuit is made up of an array of twenty one multiplication-accumulation cells based on systolic architecture. Devices can be cascaded to increase the order of the filter both vertically and horizontally. The chip has been fabricated in a 0.6 µ, low power CMOS technology and operates on 10 bit input data at over 54 Megasamples per second. The introduction gives some background to the chip design and highlights that there are few other comparable devices. Section 2 gives a brief introduction to small object detection. The chip architecture and the chip design will be described in detail in the later sections.

JPEG Image Steganalysis Using Multivariate PDF Estimates With MRF Cliques

Blind steganalysis of JPEG images is addressed by modeling the correlations among the DCT coefficients using K -variate (K = 2) p.d.f. estimates (p.d.f.s) constructed by means of Markov random field (MRF) cliques. The reasoning of using high variate p.d.f.s together with MRF cliques for image steganalysis is explained via a classical detection problem. Although our approach has many improvements over the current state-of-the-art, it suffers from the high dimensionality and the sparseness of the high variate p.d.f.s. The dimensionality problem as well as the sparseness problem are solved heuristically by means of dimensionality reduction and feature selection algorithms. The detection accuracy of the proposed method(s) is evaluated over Memon's (30.000 images) and Goljan's (1912 images) image sets. It is shown that practically applicable steganalysis systems are possible with a suitable dimensionality reduction technique and these systems can provide, in general, improved detection accuracy over the current state-of-the-art. Experimental results also justify this assertion.

Infrared non-detection of fomalhaut b: Implications for the planet interpretation

The nearby A4-type star Fomalhaut hosts a debris belt in the form of an eccentric ring, which is thought to be caused by dynamical influence from a giant planet companion. In 2008, a detection of a point source inside the inner edge of the ring was reported and was interpreted as a direct image of the planet, named Fomalhaut b. The detection was made at 600-800nm, but no corresponding signatures were found in the near-infrared range, where the bulk emission of such a planet should be expected. Here, we present deep observations of Fomalhaut with Spitzer/IRAC at 4.5 µm, using a novel point-spread function subtraction technique based on angular differential imaging and Locally Optimized Combination of Images, in order to substantially improve the Spitzer contrast at small separations. The results provide more than an order ofmagnitude improvement in the upper flux limit of Fomalhaut b and exclude the possibility that any flux from a giant planet surface contributes to the observed flux at visible wavelengths. This renders any direct connection between the observed light source and the dynamically inferred giant planet highly unlikely. We discuss several possible interpretations of the total body of observations of the Fomalhaut system and find that the interpretation that best matches the available data for the observed source is scattered light from a transient or semi-transient dust cloud. © 2012 The American Astronomical Society. All rights reserved.

Automatic Analysis of Digital Retinal Images for Glaucoma Detection

In this paper we propose a novel automated glaucoma detection framework for mass-screening that operates on inexpensive retinal cameras. The proposed methodology is based on the assumption that discriminative features for glaucoma diagnosis can be extracted from the optical nerve head structures,
such as the cup-to-disc ratio or the neuro-retinal rim variation. After automatically segmenting the cup and optical disc, these features are feed into a machine learning classifier. Experiments were performed using two different datasets and from the obtained results the proposed technique provides
better performance than approaches based on appearance. A main advantage of our approach is that it only requires a few training samples to provide high accuracy over several different glaucoma stages.