Classification of C2C e-Commerce Product Images using Deep Learning Algorithm
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 9
Abstract
C2C (consumer-to-consumer) is a business model where two individuals transact or conduct business with each other using a platform. A consumer act as a seller put their product in a platform later will be displayed to another consumer act as a buyer. This condition encourages platform to maintain high quality product information especially image that is provided by the seller. Product images need to be relevant to the product itself. It can be controlled automatically using image classification. In this paper, we carried out a research to find out the best deep learning model in image classification for e-commerce products. A dataset of 12,500 product images is collected from various web sources to be used in training and testing process. Five models are selected and fine-tuned using a uniform hyperparameter set-up. Those hyperparameters are found by using a manual process by trying a lot of hyperparameters. The testing result from every model is presented and evaluated. The result shows that NASNetLarge yield the best performance among all evaluated models with 84% testing accuracy.
Authors and Affiliations
Herdian Herdian, Gede Putra Kusuma, Suharjito Suharjito
Keywords
Related Articles
- EP ID EP645819
- DOI 10.14569/IJACSA.2019.0100925
- Views 95
- Downloads 0
Automatic Detection Of Electrocardiogram ST Segment: Application In Ischemic Disease Diagnosis
The analysis of electrocardiograph (ECG) signal provides important clinical information for heart disease diagnosis. The ECG signal consists of the P, QRS complex, and T-wave. These waves correspond to the fields induced...
E-shape Multiband Patch Antenna for 4G, C-band and S-band Applications
In this study, a new E shape mounted on minowaki island patch antenna on FR4 substrate is presented for communication systems applications. With insertion of shortening pin between patch and ground plane, the proposed st...
An Efficent Lossless Compression Scheme for ECG Signal
Cardiac diseases constitute the main cause of mortality around the globe. For detection and identification of cardiac problems, it is very important to monitor the patient's heart activities for long periods during his n...
Review of Cross-Platforms for Mobile Learning Application Development
Mobile learning management systems are very important for training purpose. But considering the present scenario, the learners are equipped with a number of mobile devices that run by different operating systems with div...
Framework for Disease Outbreak Notification Systems with an Optimized Federation Layer
Data that is needed to detect outbreaks of known and unknown diseases is often gathered from sources that are scattered in many geographical locations. Often these scattered data exist in a wide variety of formats, struc...