期刊
MULTIMEDIA TOOLS AND APPLICATIONS
卷 82, 期 8, 页码 11221-11237出版社
SPRINGER
DOI: 10.1007/s11042-022-13354-5
关键词
Biometric; Recognition; Source camera identification; Pixel non-uniformity noise
Multimodal emotion recognition has gained much attention for its potential applications, including automatic detection of pain through facial expression analysis. However, identifying the source camera of a possibly incriminating image remains a challenge. Source Camera Identification (SCI) algorithms analyze hidden features in target images to trace their origin. In cases where candidate source cameras are of the same make and model, fair assessment of these algorithms requires standard datasets. Unfortunately, existing datasets mostly comprise images taken with different camera types, such as smartphones. To address this gap, the researchers present UNISA2020, a novel dataset consisting of real-world images captured by multiple conventional digital cameras of the same type. The dataset has been carefully curated to avoid artifacts that could impact identification. Experimental analysis validates the dataset and compares the performance of an SCI algorithm on UNISA2020 and other standard datasets.
Multimodal emotion recognition has attracted a great deal of attention in recent years, with new interesting applications now being considered. One promising application is in the digital image forensics fields where, for example, it gives the possibility to automatically highlight subjects that are in pain, in digital images under examination, by analyzing their facial expressions. However, finding an image that represents a possible crime leaves the problem of identifying the device used to take the image open. Such a problem has been addressed by Source Camera Identification algorithms (SCI, for short). These algorithms analyze some features hidden in a target image to find traces left by the sensor that captured the image. A particularly challenging case is when the candidate source cameras for an image under investigation are of the same manufacturer and model. A fair and universal assessment of these algorithms is only possible if standard datasets are used for their benchmarking. However, our comprehensive analysis has shown that the majority of the datasets proposed so far contain a collection of images taken with different types of cameras, mostly smartphones. We fill this gap by presenting UNISA2020, a novel image dataset that contains a large collection of real-world images taken with multiple conventional digital cameras of the same type. The images in our dataset have been assembled so as to avoid artifacts that could negatively affect the identification process. To validate our dataset, we also performed a comparative experimental analysis to investigate the performance of an SCI reference algorithm when running on our dataset as well as on other SCI standard datasets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据