Morphological analysis of mosaic shapes with directed relationships based on attribute and relational model representations

We introduce attribute and relational representations of mosaic image models with directed relationships between regions. Attribute representations of asymmetric relational models based on stacking, ranking and integral descriptions are considered. We propose some morphological shape similarity measures based on relational models. We show that using the same oriented relational model, various morphological operators can be constructed, in particular, of Serra- or Pyt’ev type. Some constructive methods for the design of such morphological operators in an attribute and relational domains are proposed. From this consideration we also extract a new morophlogical scheme for two-stage mutual adaptive image-and-shape joint filtering: at the first step, the shape is simplified (projected) with regard to the image to be projected, and at the second step, the image is simplified (projected) with regard to the simplified (projected) shape.

Classification of Geometric Forms in Mosaics Using Deep Neural Network

The paper addresses an image processing problem in the field of fine arts. In particular, a deep learning-based technique to classify geometric forms of artworks, such as paintings and mosaics, is presented. We proposed and tested a convolutional neural network (CNN)-based framework that autonomously quantifies the feature map and classifies it. Convolution, pooling and dense layers are three distinct categories of levels that generate attributes from the dataset images by introducing certain specified filters. As a case study, a Roman mosaic is considered, which is digitally reconstructed by close-range photogrammetry based on standard photos. During the digital transformation from a 2D perspective view of the mosaic into an orthophoto, each photo is rectified (i.e., it is an orthogonal projection of the real photo on the plane of the mosaic). Image samples of the geometric forms, e.g., triangles, squares, circles, octagons and leaves, even if they are partially deformed, were extracted from both the original and the rectified photos and originated the dataset for testing the CNN-based approach. The proposed method has proved to be robust enough to analyze the mosaic geometric forms, with an accuracy higher than 97%. Furthermore, the performance of the proposed method was compared with standard deep learning frameworks. Due to the promising results, this method can be applied to many other pattern identification problems related to artworks.

Zernike Coefficient Prediction Technique for Interference Based on Generation Adversarial Network

In the paper, we propose a novel prediction technique to predict Zernike coefficients from interference fringes based on Generative Adversarial Network (GAN). In general, the task of GAN is image-to-image translation, but we design GAN for image-to-number translation. In the GAN model, the Generator’s input is the interference fringe image, and its output is a mosaic image. Moreover, each piece of the mosaic image links to the number of Zernike coefficients. Root Mean Square Error (RMSE) is our criterion for quantifying the ground truth and prediction coefficients. After training the GAN model, we use two different methods: the formula (ideal images) and optics simulation (simulated images) to estimate the GAN model. As a result, the RMSE is about 0.0182 ± 0.0035λ with the ideal image case and the RMSE is about 0.101 ± 0.0263λ with the simulated image case. Since the outcome in the simulated image case is poor, we use the transfer learning method to improve the RMSE to about 0.0586 ± 0.0035λ. The prediction technique applies not only to the ideal case but also to the actual interferometer. In addition, the novel prediction technique makes predicting Zernike coefficients more accurate than our previous research.

Optimal JPEG Quantization Table Fusion by Optimizing Texture Mosaic Images and Predicting Textures

The JPEG standard allows the use of a customized quantization table; however, it is still challenging to find an optimal quantization table timely. This work aims to solve the dilemma of balancing computational cost and image-specific optimality by introducing a new concept of texture mosaic images. Instead of optimizing a single image or a collection of representative images, the conventional JPEG optimization techniques can be applied to the texture mosaic image to obtain an optimal quantization table for each texture category. We use the simulated annealing technique as an example to validate our framework. To effectively learn the visual features of textures, we use the ImageNet pre-trained MobileNetV2 model to train and predict the new image's texture distribution, then fuse optimal texture tables to come out with an image-specific optimal quantization table. Our experiment demonstrates around 30% size reduction with a slight decrease of FSIM quality but visually indistinguishable on the evaluation datasets. Moreover, our rate-distortion curve shows superior and competitive performance against other prior works under a high-quality setting. The proposed method, denoted as JQF, achieves per image optimality for JPEG encoding with less than one second additional timing cost.

MORPHOLOGICAL IMAGE ANALYSIS BASED ON ATTRIBUTE AND RELATIONAL REPRESENTATIONS OF MOSAIC IMAGE MODELS

A unified scheme for morphological analysis based on attribute and relational representations of mosaic image models is proposed. We consider 4 main types of model representation: functional-attribute (2D feature map), functional-relational (4D relational map), structure-resource-attribute (an area list with resources and attributes), and structure-resource-relational (a graph, which nodes correspond to regions and edges – to relations and both having resource attributes). In this case, the forms of representation of the model are equivalent to each other, in the sense that they contain the same information, there is a one-to-one correspondence between them, and the formulas for the transition from one representation to another can be written out explicitly. In this scheme, the construction of specific morphological operator for some complete image model presumes the separation of this model into two parts: the guiding (modifying) part, which determines the transformation algorithm, and the guided (modifiable) part to be transformed. These two parts of the model can intersect, therefore cannot be called “variable” and “constant” components. As a basic sample, we consider the halftone Pyt’ev morphology. We explore the specifics of different-sort models, introduce the mutual models and propose different tools for creation of model-based morphological operators. Further, various other morphological systems can be described and explored using the proposed generalized approach.

SEAMLESS MOSAIC USING REMOVAL SUNGLINT TO SUPPORT A LARGE-SCALE MAPPING ACCELERATION

Mosaics of remote sensing images to support the acceleration of large-scale mapping are one of the steps in the data preparation process for dissemination to users, where generally users need seamless, mosaic images, especially on the land area. To produce a seamless mosaic image on the land area, it is sometimes constrained by the data that contains sunglints due to the direction of the recording that is opposite to the direction to the sun which causes the mosaic results to look not uniform in color on the land area. In this study, mosaics were carried out in the Pacitan area using Pleiades satellite data. From the existing problems, this study aims to compare the results of the mosaic image by removing sunglint compared to mosaic without removing sunglint. The results of this study indicate that the mosaic image by removing the sunglint produces a more seamless mosaic than the mosaic without removing the sunglint.

DESIGN AND EXPERIMENT OF A HIGH PAYLOAD FIXED WING VTOL UAV SYSTEM FOR EMERGENCY RESPONSE

With the development of UAV technologies, the advantages of hybrid VTOL UAV have been realized and taken in emergency response. But, former hybrid VTOL UAV is lack of capacities on payload and endurance, which restrict the integration of multiple sensors. In this paper, a high payload fixed wing VTOL UAV, which has 20 kg payload and more than 3 hours endurance, is used to design a UAV system for emergency response. Multiple sensors including an optronics pod, PhaseOne IXM-100 camera, high accuracy inertial navigation system and three-axis stable head are integrated with it. Based on this, specific processing software is developed to process the video data and image which could meet the requirements of emergency response in different stages. Experiment results shown that the precision of mosaic image is about 10m and the precision of orthoimage is about 1m. This work could be reference for the design and practice of UAV system with multiple sensors.