133-MEGAPIXEL1 MICRON PIXELS1st and 2nd FM generation 3D halftoning108 Megapixel1/f noise100 Hue test180 degree images1-bit matrix completion
2
2D-plus-depth video2D and 3D video2D metrics2-d scale2D to Hologram conversion2D VIEWS2D DCT2.5D reconstruction2D printing2D-TO-3D CONVERSION ARTIFACTS2-D barcodes2AFC2D2.5D2D AND 3D CONVERTIBLE DISPLAY2.5D printing2.5D PRINTING2D/3D imaging, high performance computing, imaging systems, efficient computations and storage2.5 D printing
3
3D optical scans3D data processing3D surface3D Saliency3D warping3D objects3D video processing3D scene classification3D/4D Data Processing and Filtering360VR3D mapping and localization360-degree video streaming3D depth-map360-video3D MODEL3D PRINTING3D face alignment3D Morphable Model360-degree images3D Object Detection360 degrees video360-degree art exhibition3D CAMERAS360-degree image projection3D stereo vision3D perception360 panorama3D/4D Scanning3D video3D-LUT3D-color perception3D display3D refinement3D shape indexing and retrieval3D mesh3D DIGITIZATION METHOD FOR OIL PAINTINGS3D-shooting3D position measurement of people3D Telepresence3D Data Processing3D theater program listing3D Measurement3D RECONSTRUCTION3D rigid transformations3D Vision3D Immersion3D digital halftoning3D/2D Visuals3D modeling3D range scanning360° video3D Curvelet3ARRI footage3D depth sensing360 IMAGING3D HALFTONING3D shape3D PRINTER3D printing3D Communications360-degree content3D recovery3D Printing3D Point Cloud3D affine transformation360 degree images3D Range Data Compression3D capture3D scanning3D Mapping3D modelling3D EDUCATIONAL MATERIAL3D Tracking3D scene flow estimation3D connected tube model360-degree videos3D Video Communications3D Shape Indexing and Retrieval3D/4D DATA PROCESSING AND FILTERING3D Data Sources3D Halftoning3D camera3D-HEVC3D adaptive halftoning3D image compression3D Digital Image Correlation360-degree Image3D TRANSFORMATION3D model3D Imaging3D compression3D STACK3D Modeling3D Range Data3D surface reproduction3D-printing3d3D Range Data Encoding3D Reconstruction360-degree imaging3D Color Printing3D vision3D3D encoding3D surface structure based halftoning3D glasses3D COMPRESSION AND ENCRYPTION3d video3D STIMULI3D IMAGE3D-high efficiency video coding3D visual representation3D DISPLAY360x3D scene capture3-D SHAPE RECOVERY3d mapping360 Video3A ALGORITHMS3D TV360-Degree Video Technology3D PROFILE3D cinema and TV3D USER INTERFACES3D range geometry3D Print Appearance3D colour Digital Image Correlation3D digitization and dissemination3D localization and mapping3D INTERACTION360° VIDEO3D audio3D imaging3D ACQUISITION ARCHITECTURE3D RECOVERY3D printer3D projector3D mesh simplification35MM FILM DIGITIZATION3D Scene Reconstruction and Modeling3D-Anisotropic smoothing3DCNN3D human-centered technologies3D point cloud3D-assisted features3D/4D SCANNING3D localization3D Image Processing3D RANGE IMAGING3d localization3-D RECONSTRUCTION3D MODELLING3D shape analysis360-deg quality assessment360-DEGREE IMAGE3D Video Conferencing3D Quality3D Models3D Compression3D Computer Graphics3D object shape3D-human body detection3D recursive search3D Video3-T pixel3D print3D halftoning3D SALIENCY3D Meshes3D SHAPE INDEXING AND RETRIEVAL3D and 2D3D SCENE RECONSTRUCTION AND MODELING3D Lidar3D Scene Reconstruction3D-CNN3D Iterative Halftoning360° STEREO PANORAMAS3D MESH3D reconstruction3DMM3D Compression and Encryption3D VISUALIZATION3D Gaussian splatting360-degree3D MESHES3D Display3D communications360-degree video3D displays3DSR
Images posted online present a privacy concern in that they may be used as reference examples for a facial recognition system. Such abuse of images is in violation of privacy rights but is difficult to counter. It is well established that adversarial example images can be created for recognition systems which are based on deep neural networks. These adversarial examples can be used to disrupt the utility of the images as reference examples or training data. In this work we use a Generative Adversarial Network (GAN) to create adversarial examples to deceive facial recognition and we achieve an acceptable success rate in fooling the face recognition. Our results reduce the training time for the GAN by removing the discriminator component. Furthermore, our results show knowledge distillation can be employed to drastically reduce the size of the resulting model without impacting performance indicating that our contribution could run comfortably on a smartphone.