Clinical keratoconus (KCN) detection is a challenging and time-consuming task. In the diagnosis process, ophthalmologists must revise demographic and clinical ophthalmic examinations. The latter include slit-lamb, corneal topographic maps, and Pentacam indices (PI). We propose an Ensemble of Deep Transfer Learning (EDTL) based on corneal topographic maps. We consider four pretrained networks, SqueezeNet (SqN), AlexNet (AN), ShuffleNet (SfN), and MobileNet-v2 (MN), and fine-tune them on a dataset of KCN and normal cases, each including four topographic maps. We also consider a PI classifier. Then, our EDTL method combines the output probabilities of each of the five classifiers to obtain a decision based on the fusion of probabilities. Individually, the classifier based on PI achieved 93.1% accuracy, whereas the deep classifiers reached classification accuracies over 90% only in isolated cases. Overall, the average accuracy of the deep networks over the four corneal maps ranged from 86% (SfN) to 89.9% (AN). The classifier ensemble increased the accuracy of the deep classifiers based on corneal maps to values ranging (92.2% to 93.1%) for SqN and (93.1% to 94.8%) for AN. Including in the ensemble-specific combinations of corneal maps’ classifiers and PI increased the accuracy to 98.3%. Moreover, visualization of first learner filters in the networks and Grad-CAMs confirmed that the networks had learned relevant clinical features. This study shows the potential of creating ensembles of deep classifiers fine-tuned with a transfer learning strategy as it resulted in an improved accuracy while showing learnable filters and Grad-CAMs that agree with clinical knowledge. This is a step further towards the potential clinical deployment of an improved computer-assisted diagnosis system for KCN detection to help ophthalmologists to confirm the clinical decision and to perform fast and accurate KCN treatment.
Image segmentation can be defined as a cutting or segmenting process of the digital image into many useful points which are called segmentation, that includes image elements contribute with certain attributes different form Pixel that constitute other parts. Two phases were followed in image processing by the researcher in this paper. At the beginning, pre-processing image on images was made before the segmentation process through statistical confidence intervals that can be used for estimate of unknown remarks suggested by Acho & Buenestado in 2018. Then, the second phase includes image segmentation process by using "Bernsen's Thresholding Technique" in the first phase. The researcher drew a conclusion that in case of utilizing
... Show MoreAbstract
Target costing and cleaner production are among the most important techniques in the field of cost and management accounting, which, when integrated, enable economic units to achieve the goal of cost management by reducing it by calculating cost more accurately than traditional methods.To achieve this, the researcher relied on the inductive approach in writing the theoretical framework for the research, relying on foreign and Arabic books, dissertations and university theses, foreign and Arabic research and periodicals related to the subject of the research, and relying on the descriptive and analytical approach in
... Show MoreFractal image compression gives some desirable properties like fast decoding image, and very good rate-distortion curves, but suffers from a high encoding time. In fractal image compression a partitioning of the image into ranges is required. In this work, we introduced good partitioning process by means of merge approach, since some ranges are connected to the others. This paper presents a method to reduce the encoding time of this technique by reducing the number of range blocks based on the computing the statistical measures between them . Experimental results on standard images show that the proposed method yields minimize (decrease) the encoding time and remain the quality results passable visually.
Information security is a crucial factor when communicating sensitive information between two parties. Steganography is one of the most techniques used for this purpose. This paper aims to enhance the capacity and robustness of hiding information by compressing image data to a small size while maintaining high quality so that the secret information remains invisible and only the sender and recipient can recognize the transmission. Three techniques are employed to conceal color and gray images, the Wavelet Color Process Technique (WCPT), Wavelet Gray Process Technique (WGPT), and Hybrid Gray Process Technique (HGPT). A comparison between the first and second techniques according to quality metrics, Root-Mean-Square Error (RMSE), Compression-
... Show MoreThe major objective of this study is to establish a network of Ground Control Points-GCPs which can use it as a reference for any engineering project. Total Station (type: Nikon Nivo 5.C), Optical Level and Garmin Navigator GPS were used to perform traversing. Traversing measurement was achieved by using nine points covered the selected area irregularly. Near Civil Engineering Department at Baghdad University Al-jadiriya, an attempt has been made to assess the accuracy of GPS by comparing the data obtained from the Total Station. The average error of this method is 3.326 m with the highest coefficient of determination (R2) is 0.077 m observed in Northing. While in