Using Image Feature Extraction to Identification of Ancient Ceramics Based on Partial Differential Equation

This paper presents an in-depth study and analysis of the image feature extraction technique for ancient ceramic identification using an algorithm of partial differential equations. Image features of ancient ceramics are closely related to specific raw material selection and process technology, and complete acquisition of image features of ancient ceramics is a prerequisite for achieving image feature identification of ancient ceramics, since the quality of extracted area-grown ancient ceramic image feature extraction method is closely related to the background pixels and does not have generalizability. In this paper, we propose a deep learning-based extraction method, using Eased as a deep learning support platform, to extract and validate 5834 images of 272 types of ancient ceramics from kilns, celadon, and Yue kilns after manual labelling and training learning, and the results show that the average complete extraction rate is higher than 99%. The implementation of the deep learning method is summarized and compared with the traditional region growth extraction method, and the results show that the method is robust with the increase of the learning amount and has generalizability, which is a new method to effectively achieve the complete image feature extraction of ancient ceramics. The main content of the finite difference method is to use the ratio of the difference between the function values of two adjacent points and the distance between the two points to approximate the partial derivative of the function with respect to the variable. This idea was used to turn the problem of division into a problem of difference. Recognition of ancient ceramic image features was realized based on the extraction of the overall image features of ancient ceramics, the extraction and recognition of vessel type features, the quantitative recognition of multidimensional feature fusion ornamentation image features, and the implementation of deep learning based on inscription model recognition image feature classification recognition method; three-layer B/S architecture web application system and cross-platform system language called as the architectural support; and database services, deep learning packaging, and digital image processing. The specific implementation method is based on database service, deep learning encapsulation, digital image processing, and third-party invocation, and the service layer fusion and relearning mechanism is proposed to achieve the preliminary intelligent recognition system of ancient ceramic vessel type and ornament image features. The results of the validation test meet the expectation and verify the effectiveness of the ancient ceramic vessel type and ornament image feature recognition system.

Piezoelectric Sensing Element-Assisted Ceramic Art Process Optimization and Visual Quantitative Characterization

In this paper, piezoelectric sensing elements are used to assist in the study and analysis of ceramic art process optimization and visual quantization characteristics. A series piezoelectric element impedance sensor is designed based on the resonant frequency characteristics of the series piezoelectric element. Combining the resonant frequency characteristics of the series piezoelectric element and the basic principle of the impedance method, a multisensing impedance method based on the series piezoelectric element impedance sensor is proposed. The feasibility of the multisensing impedance method for monitoring the grout compactness was verified experimentally, and the basic principle of the method was further investigated by finite element simulation. The vase-type porcelain vessels were classified according to symmetry elements to find the characteristic points, the abdominal morphology was used as the basis for classification, and the screened samples were extracted from the contours to exclude the influence of other factors on the vessel shape. By the symmetrical elements of each type of ware, the classification principle of the ware type was designed and divided into six types, and each type was further subdivided into various types to establish a typological map of Qing dynasty bottle porcelain. The information entropy redundancy that describes the uniformity of the code appearance probability and the visual redundancy that describes the human eye’s sensitivity to image content or details are all entry points that can be considered for image coding. The experimental results show that the LBP-HOG fusion features can digitally express the information of ancient ceramic ornamentation and dig and verify the evolution of ceramic ornamentation with the times from the digital quantity. The GRNN model has an excellent performance in processing small samples of ancient ceramic data.

Ancient Ceramic Casting Molds from the Southern Russian Far East: Identification of Alloy Traces via Application of Nondestructive SEM-EDS and pXRF Methods

The investigation presented in this paper is a unique assemblage of ceramic casting molds discovered at one of the sites from the Bohai period (698–926) in the territory of the southern Russian Far East. The main research aim is to recognize probable traces of metal alloys cast in ceramic molds. Nondestructive pXRF and SEM-EDS methods were used as the research instruments for detecting the expected alloys’ chemical components. As a result, the elements Pb, Sn, Cu, and As were indicated at the surfaces of the molds’ cavities with evidence of carbonization caused by the casting process. Preliminarily, two groups of alloys were distinguished: lead-bearing alloys and lead-free alloys. Our new insights are in good accordance with the results of previous investigations on chemical compositions of bronzes from the Bohai period archaeological sites of the southern Russian Far East. In particular, data on the examination of ceramic molds confirm the conclusion that various kinds of copper alloys were known and used in the bronze casting craft of the Bohai period.

Influence of Local Mineral Raw Materials On The Commercial Success of Aveiro Production of Ancient Ceramic Sugar Jars

Sugar forms were conic ceramic jars having a hole at the bottom, being used specifically for the stage of the purge of the sugar cake. These pieces played a paramount role in sugar production cycle, being used for the maturation of the sugar, and since the 15th until the beginning of the 19th centuries, the old pottery centres from Aveiro and Lisbon regions, produced heavily these “formas de açúcar” (“sugar jars”) which were exported to sugar production areas, at places as diverse as Madeira, Canaries, Cape Verde, Cuba and Brazil. Mineralogical analysis by x-ray powder diffraction was carried out on bulk samples. Chemical composition was assessed by X-Ray fluorescence. The obtained results gave important information about the composition of the studied materials, and also about their raw materials. Mineralogical and chemical data obtained in samples from Aveiro point to a local production, using the upper Cretaceous (Maastrichian) marly (dolomitic) clays and clayey sands as main raw materials. Ceramics from Barreiro (Lisbon) are in general more silicated and less carbonated, composition close to the Tagus Cenozoic Basin clays. The higher iron content of Aveiro clays favours the glazing of ceramic paste at lower temperatures, giving better mechanical resistance which can justify "their best quality", as referred to in ancient documents.

Spectroscopic Analysis of Ancient Ceramic From Agror Valley Khyber Pakhtunkhwa, Pakistan

The study of material remains has been very essential to reconstruct the past human lifestyle. Archaeologists use different scientific techniques to analyze the elemental composition of the material remains to locate the raw materials, to discover production sites and to understand ancient manufacturing technologies. Of these, Laser Induced Breakdown Spectroscopy (LIBS) method have been extensively used for the compositional analysis of different crystalline and non-crystalline materials of archaeological, historical and artistic interest for the last two decades. The present study was carried out to investigate the elemental composition of ceramic potsherds collected from the historic period. The present paper focuses on the major and minor elements identified through LIBS in the ceramic samples collected from different archaeological sites located in Mansehra, the easternmost district of Khyber Pakhtunkhwa Province of Pakistan. The LIBS results show the presence of Fe, Mg, Ca, and Na as major elements in the ancient ceramic along with traces of Si, Ti, Al and K. LIBS results show differences in the concentration of each elements present in every selected ceramic potsherds which indicates the source of raw material, production strategies and time periods of these objects were related to each other.

Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive Identification

A non-destructive identification method was developed here based on dropout deep belief network in multi-spectral data of ancient ceramic. A fractional differential algorithm was proposed to enhance the spectral details by making use of the difference between the first and second-order differential pre-process spectral data. An unsupervised multi-layer restricted Boltzmann machine (RBM) was employed to extract some high-level features during pre-training. Some weight and bias values trained by RBM were used to initialize a back propagation (BP) neural network. The RBM deep belief network was fine-tuned by the BP neural network to promote the initiative performance of network training, which helped to overcome local optimal limitation of the network due to the random initializing weight parameter. The dropout strategy has been put forward into the RBM network to solve the over-fitting of small sample spectral data. The experimental results show that the proposed method has excellent recognition performance of the ceramics by comparisons with some other ones.