In this paper, we propose a text extraction method from camera-captured document style images and propose a text segmentation method based on a color clustering method. The proposed extraction method detects text regions from the images using two low-level image features and verifies the regions through a high-level text stroke feature. The two level features are combined hierarchically. The low-level features are intensity variation and color variance. And, we use text strokes as a highlevel feature using multi-resolution wavelet transforms on local image areas. The stroke feature vector is an input to a SVM (Support Vector Machine) for verification, when needed. The proposed text segmentation method uses color clustering to the extracted text regions. We improved K-means clustering method and it selects K and initial seed values automatically. We tested the proposed methods with various document style images captured by three different cameras. We confirmed that the extraction rates are good enough to be used in real-life applications.

No abstract

Objectives. Sensitization to specific inhalant allergens is a major risk factor for the development of atopic diseases, which impose a major socioeconomic burden and significantly diminish quality of life. However, patterns of inhalant allergic sensitization have yet to be precisely described. Therefore, to enhance the understanding of aeroallergens, we performed a cluster analysis of inhalant allergic sensitization using a computational model. Methods. Skin prick data were collected from 7,504 individuals. A positive skin prick response was defined as an allergento-histamine wheal ratio ≥1. To identify the clustering of inhalant allergic sensitization, we performed computational analysis using the four-parameter unified-Richards model. Results. Hierarchical cluster analysis grouped inhalant allergens into three clusters based on the Davies-Bouldin index (0.528): cluster 1 (Dermatophagoides pteronyssinus and Dermatophagoides farinae), cluster 2 (mugwort, cockroach, oak, birch, cat, and dog), and cluster 3 (Alternaria tenus, ragweed, Candida albicans, Kentucky grass, and meadow grass). Computational modeling revealed that each allergen cluster had a different trajectory over the lifespan. Cluster 1 showed a high level (>50%) of sensitization at an early age (before 19 years), followed by a sharp decrease in sensitization. Cluster 2 showed a moderate level (10%-20%) of sensitization before 29 years of age, followed by a steady decrease in sensitization. However, cluster 3 revealed a low level (<10%) of sensitization at all ages. Conclusion. Computational modeling suggests that allergic sensitization consists of three clusters with distinct patterns at different ages. The results of this study will be helpful to allergists in managing patients with atopic diseases.

No abstract

No abstract

No abstract

No abstract

No abstract