Conference Paper

Health examination based on iris images.

DOI: 10.1109/ICMLC.2010.5580885 Conference: International Conference on Machine Learning and Cybernetics, ICMLC 2010, Qingdao, China, July 11-14, 2010, Proceedings
Source: DBLP

ABSTRACT This study combined iridology with image processing technique to conducts iris disease examination. Iridology is not to determine disease, but to reflect degeneration of organic functions, toxin precipitation and various unhealthy situations caused by mental or other factors. Iris test technique applies simple and non-invasive healthy examination method, helps the people prevent disease, and regularly follows up self-health conditions to achieve real-time prevention and treatment. The system consists of four modules: eye image capture, image preprocessing, texture feature extraction and symptomatic analysis. Following the input of eye image, the required iris part is acquired from eye images by using image preprocessing module. The texture feature extraction module utilizes 2-D Gabor filter to extract texture feature. The symptomatic analysis module uses fuzzy theory to evaluate severity of organ symptoms.

  • [Show abstract] [Hide abstract]
    ABSTRACT: Iridology is an analysis of health based on examination of the iris of the eye. One hundred forty-three patients had photographs taken of both eyes. Nine-five patients were free of kidney disease, defined as a creatinine level of less than 1.2 mg/dL (mean, 0.8 mg/dL), and 48 had kidney disease severe enough to raise the plasma creatinine level to 1.5 mg/dL or greater (mean, 6.5 mg/dL). Three ophthalmologists and three iridologists viewed the slides in a randomized sequence without knowledge of the number of patients in the two categories or any information about patient history. Iridology had no clinical or statistically significant ability to detect the presence of kidney disease. Iridology was neither selective nor specific, and the likelihood of correct detection was statistically no better than chance.
    JAMA The Journal of the American Medical Association 10/1979; 242(13):1385-9. · 30.39 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A method for rapid visual recognition of personal identity is described, based on the failure of a statistical test of independence. The most unique phenotypic feature visible in a person's face is the detailed texture of each eye's iris. The visible texture of a person's iris in a real-time video image is encoded into a compact sequence of multi-scale quadrature 2-D Gabor wavelet coefficients, whose most-significant bits comprise a 256-byte “iris code”. Statistical decision theory generates identification decisions from Exclusive-OR comparisons of complete iris codes at the rate of 4000 per second, including calculation of decision confidence levels. The distributions observed empirically in such comparisons imply a theoretical “cross-over” error rate of one in 131000 when a decision criterion is adopted that would equalize the false accept and false reject error rates. In the typical recognition case, given the mean observed degree of iris code agreement, the decision confidence levels correspond formally to a conditional false accept probability of one in about 10<sup>31</sup>
    IEEE Transactions on Pattern Analysis and Machine Intelligence 12/1993; · 5.69 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The image segmentation is very sensitive to the features used in the similarity measure and the objects type. In this paper we introduce a new segmentation algorithm based on fuzzy clustering. This method allows to incorporate spatial information which yield the result more accurate and more robust to noise. It is completely automatized with respect to the number of clusters and the setting up of membership functions. The data structure based on a Fuzzy Tree Algorithm allows to reduce the CPU time.
    Fuzzy Sets and Systems 02/2007; · 1.88 Impact Factor