Classifying metals is an essential task in all industries to make sure the materials used in the processes are safe and meet the required standards all while enhancing operational and cost effectiveness. Metal classification is crucial in processes such as quality control, recycling, green manufacturing and any other processes that rely on metal. The metallurgical domain relies on techniques for metal classification such as X-ray Fluorescence, Magnetic Induction Spectroscopy and Eddy Current Separation with regards to their speed, accuracy and cost. This work proposes a new system for thermal image based metal classification which is expected to be better in terms of effectiveness, cost and time as compared to the traditional methods. In this work, heat conductivity and specific heat characteristics of metals are taken into account to generate a thermal image map. As different metals have different conductivity and specific heat, the heat absorption and radiation map generated by thermal image can be used to identify the type of metal using a machine learning based classification method. The results show that fused with machine learning Decision Tree and Random Forest algorithms in the metal identification system can classify metals with an accuracy of 96% and 98% respectively. These results highlight how machine learning and thermal imaging can offer more precise and reliable results than traditional machinery. This approach presents a practical solution that conserves cost and time.

Security in terms of copyright measurement for digital media distribution is the most challenging task. To maintain the digital right in 3D media, a watermarking scheme is proposed for Multi-view Video plus Depth (MVD) representation to sustain against the view synthesis and RST attack. The Singular Value Decomposition (SVD) is carried out on the left and the right video sequences to find view-invariant coefficients for watermark insertion. Motion compensated Discrete Cosine Transform (DCT) based Temporal Filtering (MCDCT-TF) is used in the temporal direction to make the scheme robust against video compression attack. The 2D Discrete Wavelet Transform (2D-DWT) is processed on the temporally filtered low-pass frames as a pre-processing to get to make the SVD coefficients more connected or say correlated in between the 3D view such that robustness can be achieved against RST and view synthesis with minimum visual degradation. A set of experiments is carried out with different 3D video sequences to justify the robustness of the proposed scheme over the RST attack.

The tremendous growth in communication and media technology and the wide availability of cheaper end using devices have made 3D video communication very popular due to its immersive experience. It has been observed that a 3D video can be produced either by direct accusation using a 3D camera (say real 3D video) or by rendering from a set of 2D images (say fake 3D video). There are several occasions where it is required to distinguish between such real and fake 3D video sequences. In this paper, an algorithm is proposed which can distinguish the real 3D video from the fake one. A set of distinguishing features has been identified which are primarily based on the vertical parallax and sharpness peculiarities of object edges due to 3D acquisition process and rendering. Finally, two different supervised learning classifiers (Support Vector Machines and Linear discriminant analysis), are being trained using these features to detect the fake 3D video sequences. A comprehensive set of experiments has been carried out to justify the applicability of the proposed detection scheme over the recent existing scheme.

Detection of objects is the most popular research topic nowadays. In this regard Convolution neural network gives a direction to achieve the goal. But detection of the Stationary objects on a live camera become more challenging due to the non-rigid movement of the object. Also, most of the time stationary objects appear to be focal loss in the time of detection. So using CNN for those cases will make the scheme fragile. In this paper, Image segmentation and Kalman filter are used to rectify the focal loss to make the scheme more accurate. Here RetinaNet is used for the implementation of a better object detection scheme. As a result, it is observed that the use of RetinaNet makes the stationary object detection more accurate and the results are acceptable compared to the state of the art model.

Breast lesion localization using tactile imaging is a new and developing direction in medical science. To achieve the goal, proper image reconstruction and image registration can be a valuable asset. In this paper, a new approach of the segmentation-based image surface reconstruction algorithm is used to reconstruct the surface of a breast phantom. In breast tissue, the sub-dermal vein network is used as a distinguishable pattern for reconstruction. The proposed image capturing device contacts the surface of the phantom, and surface deformation will occur due to applied force at the time of scanning. A novel force based surface rectification system is used to reconstruct a deformed surface image to its original structure. For the construction of the full surface from rectified images, advanced affine scale-invariant feature transform (A-SIFT) is proposed to reduce the affine effect in time when data capturing. Camera position based image stitching approach is applied to construct the final original non-rigid surface. The proposed model is validated in theoretical models and real scenarios, to demonstrate its advantages with respect to competing methods. The result of the proposed method, applied to path reconstruction, ends with a positioning accuracy of 99.7%.

In recent steganographic literature, video steganography becomes popular due to its capability of accommodating higher payload. Since the video is transmitted mostly in a compressed format, compressed domain parameters are a natural choice for data embedding. In this paper, a motion vector based video steganographic method is proposed. For embedding the secret bit stream, the embedding motion vectors are selected for the homogeneous regions of the reference frame. Since homogeneous or smooth regions contain macro blocks with similar prediction error blocks, it helps to reduce the chance of detection by masking the embedding noise with similar prediction error among neighbouring macro blocks. The efficient search window and polar orientation based embedding technique are used to improve the imperceptibility against standard steganalysis schemes. A set of experiments is been carried out to justify the efficacy of the proposed scheme over the related existing steganographic methods.

In 3D image compression, depth image based rendering (DIBR) is one of the latest techniques where the center image (say the main view, is used to synthesise the left and the right view image) and the depth image are communicated to the receiver side. It has been observed in the literature that most of the existing 3D image watermarking schemes are not resilient to the view synthesis process used in the DIBR technique. In this paper, a 3D image watermarking scheme is proposed which is invariant to the DIBR view synthesis process. In this proposed scheme, 2D-dual-tree complex wavelet transform (2D-DT-CWT) coefficients of centre view are used for watermark embedding such that shift invariance and directional property of the DT-CWT can be exploited to make the scheme robust against view synthesis process. A comprehensive set of experiments has been carried out to justify the robustness of the proposed scheme over the related existing schemes with respect to the JPEG compression and synthesis view attack.

In this paper, a 3D image watermarking scheme is proposed to embed the watermark with the depth of the 3D image for depth image based rendering (DIBR) 3D image representation. To make the scheme invariant to view synthesis process, watermark is inserted with the scale invariant feature transform (SIFT) feature point locations obtained from the original image. Moreover, embedding zone for watermarking has been selected in such a way that no watermark can be inserted in the foreground object to avoid perceptible artefacts. Also, a novel watermark embedding policy is used to insert the watermark with the depth of the 3D image to resist the image processing attacks. A comprehensive set of experiments are carried out to justify the robustness of the proposed scheme.

In this paper, a novel automatic fake and the real 3D video recognition scheme is proposed to distinguish the 3D video converted from the 2D video using 2D to 3D conversion process (say fake 3D) from the 3D video captured using direct capturing of the 3D camera (say real 3D). To identify the real and fake 3D, pre-filtration is done using the dual tree complex wavelet transform to emerge the edge and vertical and horizontal parallax characteristics of real and fake 3D videos. Convolution neural network (CNN) is used to train the 3D characteristics to distinguish the fake 3D videos from the real ones. A comprehensive set of experiments has been carried out to justify the efficacy of the proposed scheme over the existing literature.

In this paper, a compressed domain drift compensated reversible watermarking scheme is proposed with a high embedding capacity and the least amount of visual quality degradation for H.265/HEVC videos. Using compressed domain syntax elements, such as motion vector and transformed residual, a set of 4 × 4 Transform Blocks (TB) of similar texture are chosen from consecutive I Frames for watermark embedding. Due to texture similarity of these selected TBs, the differences between the transformed coefficients are equal or close to zero. Utilizing this difference statistics, a multilevel watermarking is inserted in the compressed video by altering near zeros values in the difference transformed coefficients. A comprehensive set of experiments have been carried out to justify the efficacy of the proposed scheme over existing literature.

In this paper, a video watermarking scheme is proposed to embed the watermarking with the depth sequences of the respective video frames for multi-view video plus depth (MVD) based 3D video sequences. To make the scheme invariant to 3D-HEVC compression attack, motion compensated temporal filtering (MCTF) is done over the video sequences to find motion-coherent connected pixels. Scale- invariant feature transform (SIFT) is done on the temporally filtered frame to make the proposed method view invariant. Moreover, embedding zone for watermarking has been selected in such a way that no watermark can be inserted in the foreground object to avoid perceptible artefacts. Also, a novel watermark embedding policy is used to insert the watermark with the depth of the 3D video to resist the view synthesis as well as video compression attack and temporal scalable attack on the depth sequences. A comprehensive set of experiments is carried out to justify the robustness of the proposed scheme.

In this paper, a multi-view stereo image watermarking scheme is proposed to resist the RST (rotation, scaling and translation) attack. To make the scheme resilient to RST, the coefficients of Singular Value Decomposition (SVD) from both left and right views have been used for insertion of the watermark bits. 2D-DWT (Discrete wavelet transform) is used as a preprocessing step to get more correlated SVD coefficients of the left and right view such that the visual degradation due to embedding can be reduced. In this work, a blind embedding scheme is proposed by altering the selected SVD coefficients to improve the robustness of the embedding scheme. A comprehensive set of experiments have been performed to justify the robustness of the proposed scheme against RST attack. Moreover, this scheme can be used to detect the view swapping attack using DIBR technique.

In this paper, a view invariant watermarking scheme is proposed for depth image based rendering (DIBR) 3D image representation. To make the scheme invariant against view synthesis process, the watermark is inserted in the image locations selected by the SIFT (Scale-invariant feature transform) feature points. A novel SIFT feature based coefficient selection scheme has been implemented for watermark embedding by exploiting the shift invariance and directional property of the DIBR based view synthesis process. A coefficient partitioning based blind watermarking method has been included to make the scheme more efficient. A comprehensive set of experiments have been carried out to justify the robustness of the proposed scheme against the view synthesis attack.

With the huge advance in Internet technology as well as the availability of low-cost 3D display devices, 3D image transmission has become popular in recent times. Since watermarking has become regarded as a potential Digital Rights Management (DRM) tools in the past decade, 3D image watermarking is an emerging research topic. With the introduction of the Depth Image-Based Rendering (DIBR) technique, 3D image watermarking is a more challenging task, especially for synthetic view generation. In this article, synthetic view generation is regarded as a potential attack, and a blind watermarking scheme is proposed that can resist it. In the proposed scheme, the watermark is embedded into the low-pass filtered dependent view region of 3D images. Block Discrete Cosine Transformation (DCT) is used for spatial-filtration of the dependent view region to find the DC coefficient with horizontally shifted coherent regions from the left and right view to make the scheme robust against synthesis view attack. A comprehensive set of experiments have been carried out to justify the robustness of the proposed scheme over related existing schemes with respect to Stereo JPEG compression and different noise addition attacks.

Heterogeneity among the end using display devices and corresponding varying system requirements make scalable version of H.264/AVC standard more popular. Existing watermarking based authentication system may not be suitable well for this new extension, because the scalability property of the codec may itself is perceived as an attack popularly known as content adaptation attack. In this paper, a blind scalable video watermarking scheme is proposed, which is robust against quality and temporal scalability. In the proposed scheme, Discrete Cosine Transform (DCT) based temporal filtering and wavelet based spatial filtering is used for choosing suitable watermark embedding zone. Experimental evidences are provided to justify the improved robustness of the proposed scheme over existing related watermarking schemes. The visual quality of the watermarked video has also been evaluated to show the efficiency of the proposed scheme.

Camcorder based video copy attack has become a serious threat to the electronic movie distribution services. In literature, it is found that main distortions caused during cam-cording are frame blending and projection attacks. Though, several watermarking schemes exist to handle geometric distortions caused during cam-cording, very few of them are robust against temporal distortion. Based on the existing limitations of the state-of-art literature, a blind watermarking scheme which is robust against both frame blending and projection attacks is proposed in this paper. Using scale invariant feature transform (SIFT) and higher-order singular value decomposition (HOSVD), the temporal synchronization between cam-corded video and source video is achieved. Further, SIFT and log-polar transform are used together to achieve spatial synchronization of the embedding locations. The main contribution of this work is twofold, primarily it handles the frame blending and projection attacks during cam-cording and secondly it prevents the distortion in the watermark signal when different content adaptation is done specially when the quality and temporal adaptation is done in case of scalable video. A comprehensive set of experiments has been carried out to show the applicability of the proposed scheme over the existing literature.

In this paper, a 3D video watermarking scheme is proposed for depth image based rendering (DIBR) based multi view video plus depth (MVD) encoding technique. To make the scheme invariant to view synthesis process in DIBR technique, watermark is inserted in a center view which is rendered from left and right views of a 3D video frame. A low pass center view, obtained from the motion compensated temporal filtering over all the frames of a GOP, is used for embedding to reduce the temporal flickering artifacts. To make the scheme invariant to the DIBR process, 2D DT-DWT block coefficients of low-pass center view are used for embedding by exploiting its shift invariance and directional property. A comprehensive set of experiments have been carried out to justify the robustness of the proposed scheme over existing schemes with respect to compression of the 3D-HEVC video codec and synthesis view attack.

In this paper, a new steganalysis technique is proposed to detect the motion vector based steganography for the compressed videos. The proposed scheme explores the flickering effect, the changes in the prediction error and statistical anomalies in the motion vectors due to embedding to detect the presence of steganographic messages. The experimental results show that the proposed method effectively detects the data embedded in motion vector based steganographic techniques more accurately than the already existing schemes.

Due to the increasing heterogeneity among the end using devices for playing multimedia content, scalable video communication attracts significant attention in recent days. As a consequence, content authentication or ownership authentication using watermarking for scalable video stream is becoming emerging research topic. In this paper, a watermarking scheme for scalable video is proposed which is robust against spatial and quality scalability. In the proposed scheme, a DC frame is generated by accumulating DC values of non-overlapping blocks for every frame in the input video sequence. DC frame sequence is up-sampled and subtracted from the original video sequence to generate residual frame sequence. Then Discrete Cosine Transform (DCT) based temporal filtering is applied on DC as well as residual frame sequence. Watermark is embedded in low pass frames of DC frames and up sampled watermark is embedded in the low pass residual frames to achieve the graceful improvement of watermark signal in successive enhancement layer. A comprehensive set of experiments are done to justify the superiority of the proposed scheme over existing literature with respect to spatial and quality adaptation attacks as well as visual quality.

Due to enormous advancement of internet technology and display devices, 3D video becomes popular in recent times. To ensure secure media transmission, efficient authentication scheme for such 3D video sequence is a requirement. In recent past, watermarking is being regarded as a popular DRM tool for video authentication. It has been observed that video watermarking becomes a challenging task in the presence of advanced auto-stereoscopic display devices and MVD (Multi-view Video plus Depth) based encoding technique in case of 3D video. In this paper, depth image based rendering technique is proposed for blind 3D video watermarking. In this scheme, rendering technique is used to find the Z-axis of the stereo videos (left and right video). The connected regions of the Z-axis of a Group of Picture (GOP) have been filtered using the motion prediction of the video. Block DCT coefficients are used to embed the watermark signal with the selected Z-axis regions of the each video (left and right separately). A comprehensive set of experiments have been done to justify the robustness of the proposed scheme over existing schemes with respect to compression of the 3D-HEVC video codec.