Browsing by Subject "False positive"

Now showing 1 - 2 of 2

Open Access
Detection of fungal damaged popcorn using image property covariance features
(Elsevier, 2012) Yorulmaz, O.; Pearson, T. C.; Çetin, A.
Covariance-matrix-based features were applied to the detection of popcorn infected by a fungus that causes a symptom called " blue-eye" . This infection of popcorn kernels causes economic losses due to the kernels' poor appearance and the frequently disagreeable flavor of the popped kernels. Images of kernels were obtained to distinguish damaged from undamaged kernels using image-processing techniques. Features for distinguishing blue-eye-damaged from undamaged popcorn kernel images were extracted from covariance matrices computed using various image pixel properties. The covariance matrices were formed using different property vectors that consisted of the image coordinate values, their intensity values and the first and second derivatives of the vertical and horizontal directions of different color channels. Support Vector Machines (SVM) were used for classification purposes. An overall recognition rate of 96.5% was achieved using these covariance based features. Relatively low false positive values of 2.4% were obtained which is important to reduce economic loss due to healthy kernels being discarded as fungal damaged. The image processing method is not computationally expensive so that it could be implemented in real-time sorting systems to separate damaged popcorn or other grains that have textural differences.
Open Access
Impact of maintainability defects on code inspections
(ACM, 2010) Albayrak, Özlem; Davenport, David
Software inspections are effective ways to detect defects early in the development process. In this paper, we analyze the impact of certain defect types on the effectiveness of code inspection. We conducted an experiment in an academic environment with 88 subjects to empirically investigate the effect of two maintainability defects, i.e., indentation and naming conventions, on the number of functional defects found, the effectiveness of functional defect detections, and the number of false positives reported during individual code inspections. Results show that in cases where both naming conventions and indentation defects exist, the participants found minimum number of defects and reported the highest number of false positives, as compared to the cases where either indentation or naming defects exist. Among maintainability defects, indentation seems to significantly impact the number of functional defects found by the inspector, while the presence of naming conventions defects seems to have no significant impact on the number of functional defects detected. The presence of maintainability defects significantly impacts the number of false positives reported. On the effectiveness of individual code inspectors we observed no significant impact originated from the presence of indentation or naming convention defects. © 2010 ACM.