Automatic Object-Detection of School Building Elements in Visual Data: A Gray-Level Histogram Statistical Feature-Based Method

Automatic object-detection technique can improve the efficiency of building data collection for semi-empirical methods to assess the seismic vulnerability of buildings at a regional scale. However, current structural element detection methods rely on color, texture and/or shape information of the object to be detected and are less flexible and reliable to detect columns or walls with unknown surface materials or deformed shapes in images. To overcome these limitations, this paper presents an innovative gray-level histogram (GLH) statistical feature-based object-detection method for automatically identifying structural elements, including columns and walls, in an image. This method starts with converting an RGB image (i.e. the image colors being a mix of red, green and blue light) into a grayscale image, followed by detecting vertical boundary lines using the Prewitt operator and the Hough transform. The detected lines divide the image into several sub-regions. Then, three GLH statistical parameters (variance, skewness, and kurtosis) of each sub-region are calculated. Finally, a column or a wall in a sub-region is recognized if these features of the sub-region satisfy the predefined criteria. This method was validated by testing the detection precision and recall for column and wall images. The results indicated the high accuracy of the proposed method in detecting structural elements with various surface treatments or deflected shapes. The proposed structural element detection method can be extended to detecting more structural characteristics and retrieving structural deficiencies from digital images in the future, promoting the automation in building data collection.

BI-RADS classification and gray level histogram of malignant mammary tumors in bitches

ABSTRACT: Mammary tumor is the most frequent among the tumors that affect canine females, with relevant importance in veterinary medicine. The objective of this study was to determine the image characteristics of mammary tumors in female dogs, and compare different ultrasonographic techniques for neoplastic evaluation. During the experiment, 30 bitches with presence of nodular lesion in the mammary gland were used. Initially females were submitted to clinical and laboratory evaluations, and subsequent to the ultrasound examination of the tumor mass, as well as abdominal ultrasound and thoracic x-ray for the metastasis investigation. Quantitative analysis by histogram of the gray levels and categorization of the tumor masses by the BI-RADS system were performed. Later, the bitches were submitted to surgical resection of the tumors, where samples of the neoplastic tissue were collected for histopathological analysis. Carcinoma in mixed tumor showed a higher rate (33.3%), and the malignancy degree of epidermal tumors were classified in grade 1 (n=9), grade 2 (n=12) and grade 3 (n=3). Malignancy degree showed positive correlation with BI-RADS (r=0.55; P<0.05) and with the parameter echotexture - histogram base width (r=0.42, P<0.05). BI-RADS graduation also showed a positive correlation with the echotexture parameters (standard deviation of average echogenicity r=0.66, P<0.05 and base width r=0.55, P<0.05). It was concluded that the BI-RADS method in combination with the echotexture of tumors, can be used to evaluate mammary tumors in dogs and establish the planning of treatment.

PENGARUH FAKTOR EKSPOSI TERHADAP KUALITAS CITRA RADIOGRAFI

The research on the influence of exposure factor on radiographic image quality has been conducted. This research uses phantom, water in plastic container as human substitute with focus film distance (FFD) 100 cm and broad field of irradiation 15 cm × 15 cm. The exposure conditions are given by exposure factors including variations in tube voltages of 60 kV, 65 kV, 70 kV, 75 kV, 80 kV called standard techniques or routine voltage techniques and the time flow is as big as 20 mAs, 25 mAs and 30 mAs. The results showed that the image quality will decrease with the use of current and time high. Image quality can be seen on gray-level histogram using java Image-J Basics version 1.38 software to get optimum value from exposure factor on image quality.

Tissue Characterization with Gray-level Histogram Width in Obstetrics and Gynecology

ABSTRACT Aim Clinical ultrasound tissue characterization, using usual B-mode devices. Materials and methods Malignant neoplasia in ovary, uterine cervix, and endometrium; placental intervillous space fibrin deposit; fetal growth restriction; fetal brain, fetal lung immaturity; meconium-stained amniotic fluid and healthy adult liver; Tissue was characterized by gray-level histogram width (GLHW) divided by full gray scale length. Results Malignant GLHW was higher than in benign one (it was malignant if the GLHW was 50% or more in ovary, uterine cervix, and endometrium). The GLHW of placental fibrin deposit was higher than normal placenta. It was reduced by heparin and normal neonate was obtained. Fetal brain echo density, immature fetal lung, and meconium-stained amniotic fluid were diagnosed by GLHW, and normal adult liver GLHW was studied. Helsinki declaration was followed. Conclusion The GLHW tissue characterization objectively diagnosed ultrasound B-mode image in obstetrics and gynecology; thus, it would also be applied in common adult human cases. How to cite this article Maeda K, Kihaile PE, Ito T, Utsu M, Yamamoto N, Serizawa M. Tissue Characterization with Gray-level Histogram Width in Obstetrics and Gynecology. Donald School J Ultrasound Obstet Gynecol 2017;11(1):7-10.