The retinal illness that causes vision loss frequently on the globe is glaucoma. Hence, the earlier detection of Glaucoma is important. In this article, modified AlexNet deep leaning model is proposed to category the ...
详细信息
The retinal illness that causes vision loss frequently on the globe is glaucoma. Hence, the earlier detection of Glaucoma is important. In this article, modified AlexNet deep leaning model is proposed to category the source retinal images into either healthy or Glaucoma through the detection and segmentations of optic disc (OD) and optic cup (OC) regions in retinal pictures. The retinal images are preprocessed and OD region is detected and segmented using circulatory filter. Further, OC regions are detected and segmented using K-means classification algorithm. Then, the segmented OD and OC region are classified and trained by the suggested AlexNet deep leaning model. This model classifies the source retinal image into either healthy or Glaucoma. Finally, performance measures have been estimated in relation to ground truth pictures in regards to accuracy, specificity and sensitivity. These performance measures are contrasted with the other previous Glaucoma detection techniques on publicly accessible retinal image datasets HRF and RIGA. The suggested technique as described in this work achieves 91.6% GDR for mild case and also achieves 100% GDR for severe case on HRF dataset. The suggested method as described in this work achieves 97.7% GDR for mild case and also achieves 100% GDR for severe case on RIGA dataset. AIM: Segmenting the OD and OC areas and classifying the source retinal picture as either healthy or glaucoma-affected. METHODS: The retinal images are preprocessed and OD region is detected and segmented using circulatory filter. Further, OC region is detected and segmented using K-means classification algorithm. Then, the segmented OD and OC region classified are and trained by the suggested AlexNet deep leaning model. RESULTS: The suggested method as described in this work achieves 91.6% GDR for mild case and also achieves 100% GDR for severe case on HRF dataset. The suggested method as described in this work achieves 97.7% GDR for mild case and also achie
India is a sovereign, socialist, and secular country where democracy is a form of government in which citizens exercise power by voting. Polling is the survey of a particular group of people who cast votes in an elect...
详细信息
A Flying Ad-hoc Network (FANET) is a group of Unmanned Aerial Vehicles (UAVs) that operate in an ad-hoc fashion, like Mobile Ad-hoc networks (MANET) and Vehicle Ad-hoc networks (VANET). The application of UAVs ha...
详细信息
This study investigates the potential use of blockchain technology and smart contracts to construct a decentralised land registry system. It looks at the problems with traditional land registry systems and provides a ...
详细信息
The stability and security of the Internet's routing infrastructure, largely dependent on the Border Gateway Protocol (BGP), are critical for ensuring reliable global connectivity. Anomalous routing behavior can d...
详细信息
Voice analysis in Natural Language Processing (NLP) involves the processing of spoken language to develop applications such as speech recognition, synthesis, and speaker identification. This survey explores the phonet...
详细信息
The vast changes in the computing utilization have created a need with the improvised resource availability and reliability. The virtualization of servers and data centers to increase their efficiency has transformed ...
详细信息
Quantum secret sharing (QSS) is a significant branch of quantum cryptography and can be widely used in various applications. Quantum secret sharing schemes can be developed by utilizing different features of quantum m...
详细信息
In this paper, a BCI-based machine learning method is proposed to predict the attention lapse of the driver. An EEG headset is used to capture brain activity from different regions of the human brain. The data is furt...
详细信息
Fraud and Identity Theft constitute for huge financial loss to the telecom industry and telecom fraud accounts for a major cause of revenue loss. Among them, roaming fraud has the highest impact over network service p...
详细信息
暂无评论