What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Computer vision
- Algorithm
Jessica Fridrich spends much of her time researching Artificial intelligence, Steganography, Steganalysis, Computer vision and Embedding.
Her work in the fields of Artificial intelligence, such as Digital image, Grayscale, Noise and Image noise, intersects with other areas such as Least significant bit.
Her biological study spans a wide range of topics, including Pixel, JPEG, Theoretical computer science and Algorithm.
Jessica Fridrich interconnects Histogram, Lossless JPEG and Discrete cosine transform in the investigation of issues within JPEG.
Her Steganalysis research includes themes of Quantization, Cover, Steganography tools, Quantization and Pattern recognition.
Her research in Digital watermarking intersects with topics in Watermark, Lossy compression and Data compression.
Her most cited work include:
- Digital Watermarking and Steganography (1323 citations)
- Rich Models for Steganalysis of Digital Images (903 citations)
- Digital camera identification from sensor pattern noise (878 citations)
What are the main themes of her work throughout her whole career to date?
Her main research concerns Artificial intelligence, Steganography, Steganalysis, Computer vision and Embedding.
Her study connects Pattern recognition and Artificial intelligence.
Her Steganography research includes elements of JPEG, Theoretical computer science, Discrete cosine transform, Pixel and Algorithm.
In her research on the topic of JPEG, JPEG 2000 is strongly related with Lossless JPEG.
Jessica Fridrich combines subjects such as Data mining, Feature, Steganography tools, Feature vector and Histogram with her study of Steganalysis.
She has researched Embedding in several fields, including Information protection policy, Image, Grayscale and Linear code.
She most often published in these fields:
- Artificial intelligence (60.50%)
- Steganography (59.66%)
- Steganalysis (44.54%)
What were the highlights of her more recent work (between 2015-2021)?
- Steganography (59.66%)
- Artificial intelligence (60.50%)
- JPEG (32.77%)
In recent papers she was focusing on the following fields of study:
Her primary areas of study are Steganography, Artificial intelligence, JPEG, Steganalysis and Pattern recognition.
Her Steganography research incorporates themes from Pixel, Algorithm and Theoretical computer science.
Her study looks at the relationship between Artificial intelligence and topics such as Computer vision, which overlap with Scalability.
The various areas that Jessica Fridrich examines in her JPEG study include Quantization, Transform coding, Discrete cosine transform, Covariance matrix and Lossless JPEG.
Her Steganalysis study also includes fields such as
- Data mining that intertwine with fields like Selection,
- Curse of dimensionality which is related to area like Dimensionality reduction.
Her study in the field of Convolutional neural network and Feature extraction also crosses realms of Least significant bit.
Between 2015 and 2021, her most popular works were:
- Content-Adaptive Steganography by Minimizing Statistical Detectability (206 citations)
- Deep Residual Network for Steganalysis of Digital Images (155 citations)
- Steganalysis Features for Content-Adaptive JPEG Steganography (93 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Algorithm
Jessica Fridrich mainly investigates Artificial intelligence, Steganalysis, Steganography, Computer vision and Pattern recognition.
Her primary area of study in Artificial intelligence is in the field of Deep learning.
Jessica Fridrich has included themes like Data mining and Selection in her Steganalysis study.
Her studies deal with areas such as JPEG and Noise as well as Steganography.
Her study focuses on the intersection of Computer vision and fields such as Embedding with connections in the field of Kernel.
Her work carried out in the field of Pattern recognition brings together such families of science as Histogram and Lossless JPEG.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
