Complex Texture Research Articles

Geochemistry of scheelite from Jiangligou skarn W-(Cu-Mo) deposit in the West Qinling orogenic belt, Northwest China: Implication on the multistage ore-forming processes

The Jiangligou skarn W-(Cu-Mo) deposit is a typical scheelite-dominated skarn deposit located in the West Qinling orogenic belt, northwestern China, hosting around 42, 000 tons of WO3 at an average grade of 1% with byproducts of Cu and Mo. Four generations of scheelite (Sch Ⅰ, Sch Ⅱ, SchIII, and SchIV) were recognized according to the mineral assemblages, inner textural, and geochemistry features. REE patterns of Sch Ⅰ have a close relationship with the garnet and diopside-hedenbergite and show significant LREE-enrichment and HREE-depletion, with δEu varying from negative (Sch Ⅰb) to positive (Sch Ⅰa). Sch Ⅱ grains show complex inner textures, zoning, syn-crystallization fractures, and filling, thus can be divided into four sub-generations with characteristic “flat” REE patterns. The early generation of scheelite gradually shifts from MREE-enriched with negative δEu (Sch Ⅱa and Sch Ⅱb) to MREE-depleted with positive δEu (Sch Ⅱc) or to lower REE with the same REE patterns (Sch Ⅱd). Sch III grains are commonly found in the sulfides overprinted ores, however, they have distinct REE patterns: Sch IIIa has relatively enriched MREE with negative δEu, while Sch IIIb is MREE depleted with positive δEu and negative δCe. The Sch IV has the largest (La/Lu)N with HREE down to the detection limit. Texture evidence implies that this may be due to later hydrothermal alteration which significantly removed the HREE. The Ca vacancy and Nb-REE coupled substitution dominantly account for the REE pattern of Sch Ⅰ, III, IV and Sch Ⅱ respectively. Revised batch crystallization modelling calculation on Sch Ⅱ and Sch III proved that the variation of δEu, MREE and Ce are controlled by the relatively low Eu2+/Eu3+ and Ce3+/Ce4+ ratios under relatively reduced conditions, and high Eu2+/Eu3+ and low Ce3+/Ce4+ ratios under relative oxidized conditions during scheelite precipitation. The extra HREE depletion of Sch Ⅱ from the measured data is interpreted as the low concentration of HREE in the ore-forming fluid caused by the precipitation of previous skarn minerals. This is also the main control in the depletion of HREE in Sch Ⅰ. Besides, the oxide condition change is also reflected by the Mo content change of the scheelite. Varied REE patterns of the four scheelite generations imply that at least four large volumes of flux of ore-forming fluids account for the whole scheelite mineralization.

Image inpainting via Smooth Tucker decomposition and Low-rank Hankel constraint

Image inpainting, aiming at exactly recovering missing pixels from partially observed entries, is typically an ill-posed problem. As a powerful constraint, low-rank priors have been widely applied in image inpainting to transform such problems into well-posed ones. However, the low-rank assumption of original visual data is only in an approximate mode, which in turn results in suboptimal recovery of fine-grained details, particularly when the missing rate is extremely high. Moreover, a single prior cannot faithfully capture the complex texture structure of an image. In this paper, we propose a joint usage of Smooth Tucker decomposition and Low-rank Hankel constraint (STLH) for image inpainting, which enables simultaneous capturing of the global low-rankness and local piecewise smoothness. Specifically, based on the Hankelization operation, the original image is mapped to a high-order structure for capturing more spatial and spectral information. By employing Tucker decomposition for optimizing the Hankel tensor and simultaneously applying Discrete Total Variation (DTV) to the Tucker factors, sharper edges are generated and better isotropic properties are enhanced. Moreover, to approximate the essential rank of the Tucker decomposition and avoid facing the uncertainty problem of the upper-rank limit, a reverse strategy is adopted to approximate the true rank of the Tucker decomposition. Finally, the overall image inpainting model is optimized by the well-known alternate least squares (ALS) algorithm. Extensive experiments show that the proposed method achieves state-of-the-art performance both quantitatively and qualitatively. Particularly, in the extreme case with 99% pixels missed, the results from STLH are averagely ahead of others at least 0.9dB in terms of PSNR values.

Review of deep learning methods for remote sensing satellite images classification: experimental survey and comparative analysis

Classification and analysis of high-resolution satellite images using conventional techniques have been limited. This is due to the complex characteristics of the imagery. These images are characterized by features such as spectral signatures, complex texture and shape, spatial relationships and temporal changes. In this research, we present the performance evaluation and analysis of deep learning approaches based on Convolutional Neural Networks and vision transformer towards achieving efficient classification of remote sensing satellite images. The CNN-based models explored include ResNet, DenseNet, EfficientNet, VGG and InceptionV3. The models were evaluated on three publicly available EuroSAT, UCMerced-LandUse and NWPU-RESISC45 datasets containing categories of images. The models achieve promising results in accuracy, recall, precision and F1-score. This performance demonstrates the feasibility of Deep Learning approaches in learning the complex and in-homogeneous features of the high-resolution remote sensing images.

Deep Neural Network for Blind Visual Quality Assessment of 4K Content

The 4K content can deliver a more immersive visual experience to consumers due to the huge improvement in spatial resolution. However, the high spatial resolution brings a great challenge for video transmission and storage. Therefore, it is necessary to compress or downscale the 4K content before transmitting it to end-users. Existing blind image quality assessment (BIQA) methods are not suitable for 4K contents due to the high spatial resolution and specific distortions caused by upscaling methods. In this paper, we propose a deep learning-based BIQA model for 4K content, aiming to recognize true and pseudo 4K content and meanwhile evaluate their visual quality. Considering the characteristic that high spatial resolution can represent more abundant high-frequency information, we first propose a Grey-level Co-occurrence Matrix (GLCM) based texture complexity measure to select three representative image patches from a 4K image, which can reduce the computational complexity and is proven to be very effective for the overall quality prediction. Then, we extract various visual features from the intermediate layers of the convolutional neural network (CNN) and integrate them into the quality-aware feature representation. Finally, two multilayer perception (MLP) networks are utilized to map the quality-aware features into the class probability and the quality score of each patch respectively. The overall quality index is obtained through averaging the results of all patches. The proposed model is trained via the multi-task learning manner and the uncertainty principle is introduced to balance the losses of the classification and regression tasks. The experimental results show that the proposed model outperforms all compared BIQA metrics on four 4K content quality assessment databases.

Different methods for textural evaluation of freeze-dried candies during storage.

The textural changes during storage of two freeze-dried candies developed from blackcurrant fruits, unflavored yogurt, and different alternative sweeteners, one sweetened with honey/isomalt (HI) and another sweetened with isomalt/stevia (IS), were analyzed using three different methods (instrumental, sensory, and image analysis). Fresh candies were in the supercooled state and presented different structural and textural characteristics (HI: compact and homogeneous, and IS: porous and crunchy), with Fmax values of 139 ± 14 and 174 ± 16 N for HI and IS, respectively. After storage, the instrumental analysis showed approximately 60% average drop in Fmax and W values, in agreement with the decrease observed by sensory analysis in hardness, fracturability, and crispness. Image analysis showed an increase in parameters related to the homogeneity and the uniformity/smoothness for HI. Pearson's correlation coefficients analysis showed that there was a good correlation between the three techniques used, suggesting that the joint use of these methods could be performed for a better understanding of complex food texture.

Mixed Receptive Fields Augmented YOLO with Multi-Path Spatial Pyramid Pooling for Steel Surface Defect Detection.

Aiming at the problems of low detection efficiency and poor detection accuracy caused by texture feature interference and dramatic changes in the scale of defect on steel surfaces, an improved YOLOv5s model is proposed. In this study, we propose a novel re-parameterized large kernel C3 module, which enables the model to obtain a larger effective receptive field and improve the ability of feature extraction under complex texture interference. Moreover, we construct a feature fusion structure with a multi-path spatial pyramid pooling module to adapt to the scale variation of steel surface defects. Finally, we propose a training strategy that applies different kernel sizes for feature maps of different scales so that the receptive field of the model can adapt to the scale changes of the feature maps to the greatest extent. The experiment on the NEU-DET dataset shows that our model improved the detection accuracy of crazing and rolled in-scale, which contain a large number of weak texture features and are densely distributed by 14.4% and 11.1%, respectively. Additionally, the detection accuracy of inclusion and scratched defects with prominent scale changes and significant shape features was improved by 10.5% and 6.6%, respectively. Meanwhile, the mean average precision value reaches 76.8%, compared with the YOLOv5s and YOLOv8s, which increased by 8.6% and 3.7%, respectively.

Cork classification based on multi-scale faster-RCNN with machine vision

In traditional industrial production, the classification of cork mainly adopts manual operation. Due to round cork blocks with complex textures, manual sorting is time-consuming and often leads to inefficiency. It will lead to inefficiency and a high error rate. Therefore, an automatic cork sorting system is urgently required to replace manual operation. In this paper, an advanced deep-learning method based on machine vision is adopted to detect the surface of corks and classify them automatically. To robustly detect the texture of cork profile, a Multiple Scale Faster R-CNN based on the upper and lower layers (UMS-FRCNN) approach is proposed. The network consists of a region proposal component and the region-of-interest (RoI) detection component. There are two main contributions in our proposed network, which play a significant role in achieving state-of-the-art performance in cork classification. Firstly, the multi-scale information is grouped in two aspects: region suggestion and RoI detection, to detect on small cork texture regions. Secondly, the convolution Region Proposal Network (RPN) is used to generate the candidate regions of the UMS-FRCNN model to improve the classification accuracy. The experimental results show that our method not only can accurately classify the corks but also has better performance than the Faster RCNN. Compared with other methods, our method has the advantages of high precision, less time-consuming, and no dependence labeling. Our work has been successfully utilized in a cork production plant.

Automated diagnosis and management of follicular thyroid nodules based on the devised small-datasets interpretable foreground optimization network deep learning: A multicenter diagnostic study.

Currently, follicular thyroid carcinoma (FTC) has relatively low incidence with a lack of effective preoperative diagnostic means. To reduce the need for diagnostic invasive procedures and to address information deficiencies inherent in a small-dataset, we utilized interpretable foreground optimization network deep learning to develop a reliable preoperative FTC detection system. In this study, a deep learning model (FThyNet) was established using preoperative ultrasound images. Data on patients in training and internal validation cohort (n=432) were obtained from XXX Hospital, China. Data on patients in external validation cohort (n=71) were obtained from four other clinical centers. We evaluated the predictive performance of FThyNet and its ability to generalize across multiple external centers and compared the results yielded with assessments from physicians directly predicting FTC outcomes. In addition, the influence of texture information around the nodule edge on the prediction results was evaluated. FThyNet had a consistently high accuracy in predicting FTC with area under the receiver operating characteristic curve (AUC) of (89.0% [95% CI 87.0-90.9]). Particularly, the AUC for grossly invasive-FTC reached 90.3%, which was significantly higher than that of the radiologists (56.1% [95% CI 51.8-60.3]). The parametric visualization study found that those nodules with blurred edges and relatively distorted surrounding textures were more likely to have FTC. Furthermore, edge texture information played an important role in FTC prediction with an AUC of (68.3% [95% CI 61.5-75.5]), and highly invasive malignancies had the highest texture complexity. FThyNet could effectively predict FTC, provide explanations consistent with pathological knowledge, and improve clinical understanding of the disease.

Local to non-local: Multi-scale progressive attention network for image restoration

Image restoration (IR) tasks aim to form a balance between complex textures and spatial details. To this end, the combination of local and non-local attention mechanisms has been well studied in recent years. However, existing local attention-based modules ignore the interaction between channel and spatial attention, while non-local attention operations solely focus on short-range or long-range dependency. To overcome these problems, a novel multi-scale progressive attention network is proposed in this paper, which is termed as MPANet. The proposed MPANet is composed of two parts, a local multi-scale feature extractor and a window-dilation self-attention module. In the local multi-scale feature extractor, a single-scale feature enhancement strategy is designed to model the correlation between channel and spatial dimensions, and a multi-scale feature fusion strategy is applied to further exchange contextual information across all the scales. Furthermore, the window-dilation self-attention is introduced to establish global representation while preserving local details. Experimental results on four IR tasks demonstrate that the proposed MPANet outperforms the state-of-the-art methods in both quantitative results and visual perception.

An Adaptive CU Split Method for VVC Intra Encoding

In order to reduce the coding complexity and ensure that versatile video coding (H.266/VVC) effectively maintains the equilibrium between coding efficiency and quality in the coding process, an adaptive coding unit (CU) split method for intra encoding is proposed in this paper. First, the coding speed of CU division is accelerated by an iterative algorithm based on the interval relation of texture complexity energy. Then, according to the relationship between texture features and CU segmentation patterns, the Scharr edge gradient operator algorithm is used to describe the texture information and the threshold. Texture uniformity, directionality, and subblock discrepancy are analyzed and discussed, respectively. Finally, the optimal segmentation pattern is determined based on the texture information to adaptively skip unnecessary segmentation modes. The results show that the algorithm can save 45.2% of the overall coding time on average with an average cost of 0.51% Bjontegaard delta bit rate (BDBR). The algorithm ensures the coding quality while reducing the computational complexity.

Material structure segmentation method based on graph attention

With the development and integration of multiple disciplines, the integration of computer vision and materials science has greatly changed the original materials research methods. Existing methods can effectively segment the image of a specific scene, but there is no general method to segment and analyze the image of material accurately. To solve the problems of complex texture, blurred boundary and low contrast in material image, we propose a method that relies on multidimensional feature fusion to train the network more effectively with limited and available annotation samples. The architecture consists of an encoder, a graph attention module, a multi-scale feature fusion module and a decoder. We show that such a network can be trained end-to-end from the image. In electron microscope image, the segmentation results are superior to many previous advanced methods. Using this method, we can accurately identify multiple structures in material images, which provides important insights for multiphase segmentation of material images and searching for new mechanisms of structural transformation in material science.

Super-resolution of X-ray CT images of rock samples by sparse representation: applications to the complex texture of serpentinite

X-ray computed tomography (X-ray CT) has been widely used in the earth sciences, as it is non-destructive method for providing us the three-dimensional structures of rocks and sediments. Rock samples essentially possess various-scale structures, including millimeters to centimeter scales of layering and veins to micron-meter-scale mineral grains and porosities. As the limitations of the X-ray CT scanner, sample size and scanning time, it is not easy to extract information on multi-scale structures, even when hundreds meter scale core samples were obtained during drilling projects. As the first step to overcome such barriers on scale-resolution problems, we applied the super-resolution technique by sparse representation and dictionary-learning to X-ray CT images of rock core sample. By applications to serpentinized peridotite, which records the multi-stage water–rock interactions, we reveal that both grain-shapes, veins and background heterogeneities of high-resolution images can be reconstructed through super-resolution. We also show that the potential effectiveness of sparse super-resolution for feature extraction of complicated rock textures.

Exploring microstructure and petrophysical properties of microporous volcanic rocks through 3D multiscale and super-resolution imaging

Digital rock physics offers powerful perspectives to investigate Earth materials in 3D and non-destructively. However, it has been poorly applied to microporous volcanic rocks due to their challenging microstructures, although they are studied for numerous volcanological, geothermal and engineering applications. Their rapid origin, in fact, leads to complex textures, where pores are dispersed in fine, heterogeneous and lithified matrices. We propose a framework to optimize their investigation and face innovative 3D/4D imaging challenges. A 3D multiscale study of a tuff was performed through X-ray microtomography and image-based simulations, finding that accurate characterizations of microstructure and petrophysical properties require high-resolution scans (≤ 4 μm/px). However, high-resolution imaging of large samples may need long times and hard X-rays, covering small rock volumes. To deal with these limitations, we implemented 2D/3D convolutional neural network and generative adversarial network-based super-resolution approaches. They can improve the quality of low-resolution scans, learning mapping functions from low-resolution to high-resolution images. This is one of the first efforts to apply deep learning-based super-resolution to unconventional non-sedimentary digital rocks and real scans. Our findings suggest that these approaches, and mainly 2D U-Net and pix2pix networks trained on paired data, can strongly facilitate high-resolution imaging of large microporous (volcanic) rocks.

Directed laser deposition of super duplex stainless steel: Microstructure, texture evolution, and mechanical properties

Microstructure and texture evolution of directed-laser deposited super-duplex stainless-steel, in the as-received block, were characterized using light and electron microscopies and electron backscattered diffraction. Mechanical properties in different directions were studied. Local FCC-depleted and FCC-rich zones and extensive precipitation of oxides were detected at the matrix wherein the different types of reformed austenite were surrounded by the elongated coarse ferrite. A vertical gradient of austenite content, caused by overall change in cooling rate, generated a waning hardness distribution along the building direction. The texture of austenite across the different deposition layers was not as intense as that of the ferrite. A dominant ⟨001⟩ ⫽ND fibre, embedding strong Cube {001}⟨100⟩, was calculated for ferrite on the layer away from the bottom while the Goss {011}⟨100⟩ appeared in the layer near the building substrate due to the considerable epitaxially developed grains. The less intensified multi-component texture of austenite at the layer near the substrate changed to ⟨011⟩ ⫽ND fibre adorned by Rotated-Goss and Goss components at the upper layers where an incomplete fibre {001}⟨uvw⟩ with a major Rotated-Cube was also partially inherited from the parent phase. The inter-phase boundaries obeying Kurdjumov-Sachs orientation relationship were predominantly formed at all layers. A slight increase of Σ3 coincidence site lattice interfaces was observed in austenite across the build direction. The possible mechanical anisotropy was depressed due to complex and multi-component transformation texture of the austenite. The material showed brittleness corresponding to significantly high tensile strength and low impact toughness.

Learning spectral-spatial representations from VHR images for fine-scale crop type mapping: A case study of rice-crayfish field extraction in South China

Accurate information on crop type spatial distributions is crucial for yield estimation, agroecological modeling, and agrarian policy development. In comparison with moderate resolution (10–30 m) satellite images, very high-resolution (VHR, ≤ 1 m) images are superior at describing the spatial details and complex texture features of agricultural land. However, VHR images generally suffer from insufficient spatiotemporal coverage and high spectral variation in crop type, making fine-scale crop type mapping at regional or larger scales challenging. In this study, we developed a novel data-driven residual attention U-shape network (RAUNet) to identify crop types at the regional scale based on VHR images. RAUNet was adapted from UNet by introducing a residual module and a gated attention mechanism to strengthen the multilevel representation of crop features from VHR images. We selected rice-crayfish fields (RCFs) in Hubei Province, China, as the case crop type and area to test the performance of RAUNet. Seven models, including RAUNetpan, ResUNet, AttnUNet, UNet, DeepLabV3 + and random forest at the pixel and object levels, were adopted for comparison with RAUNet. Moreover, the model transferability was evaluated over regions with different agricultural landscapes. Our results showed that RAUNet-derived RCF maps obtained an average F1-score and MCC of 0.90 and 0.85 at different cultivation stages, which significantly outperformed other methods. Additionally, RAUNet had good spatiotemporal transferability, with an average F1-score and MCC of 0.93 and 0.88 in four transfer areas. The visualization results of the attention weights indicated RAUNet’s prominent capability in combining useful and relevant information from different feature levels to produce refinement predictions for the target crop type. Furthermore, the high-level features derived from RAUNet can well separate RCFs and non-RCFs over different landscapes, which were also consistent across different cultivation periods. These encouraging results suggest that RAUNet works well for fine-scale crop type mapping in smallholder farming systems, and it is an efficient method for land cover mapping based on VHR images at the regional scale.

Impact of Apricot Pulp Concentration on Cylindrical Gel 3D Printing.

The process of 3D food printing is a rapidly growing field that involves the use of specialized 3D printers to produce food items with complex shapes and textures. This technology allows the creation of customized, nutritionally balanced meals on demand. The objective of this study was to evaluate the effect of apricot pulp content on printability. Additionally, the degradation of bioactive compounds of gels before and after printing was evaluated to analyze the effect of the process. For this proposal, physicochemical properties, extrudability, rheology, image analysis, Texture Profile Analysis (TPA), and bioactive compounds content were evaluated. The rheological parameters lead to higher mechanical strength and, thus, a decrease in elastic behavior before and after 3D printing as the pulp content increases. An increase in strength was observed when the pulp content increased; thus, sample gels with 70% apricot pulp were more rigid and presented better buildability (were more stable in their dimensions). On the other hand, a significant (p < 0.05) degradation of total carotenoid content after printing was observed in all samples. From the results obtained, it can be said that the gel with 70% apricot pulp food ink was the best sample in terms of printability and stability.

Texture and geochemistry of sphalerite from the Chitudian Pb-Zn-Ag deposit, southern margin of the North China Craton: Implications for the enrichments of Cd, Ga, and In

The Chitudian Pb-Zn-Ag deposit, located in the southern margin of the North China Craton (SNCC), is a typical magmatic-hydrothermal deposit, where sphalerite is the predominate ore mineral with significant concentrations of critical metals, including Ga, In, and Cd. However, previous studies paid little attention to the critical metals in the deposit. This study carried out in-suit elemental analysis on the sphalerite from the Chitudian deposit, aiming to constrain the spatial distribution and enrichment mechanism of critical metals. In the Chitudian deposit, five types of sphalerite were identified (Z-Sp, Y-Sp1, Y-Sp2, X-Sp1, and X-Sp2), which differ in color, texture, and chemical composition. The concentrations of Cd, Ga, and In of these sphalerites range from 1440 to 5145 ppm, 0.53 to 528 ppm, and 0.75 to 2113 ppm, respectively. In detail, Cd is mainly concentrated in the sphalerites from the hydrothermal vein-type orebodies relative to skarn-type orebodies. Indium is progressively depleted from granite-proximal locations to granite-distal locations, and the Fe-rich sphalerite is an excellent host of In. Gallium enrichment is only observed in the tectonically deformed location of the sulfide ore vein, where the Ga-rich sphalerite is poor in Fe and shows a complex texture. Microanalysis conducted on the Ga-rich sphalerite suggested that Ga, together with In, Sn, and Cu, are removed from the deformed sphalerite by mineral-fluid interaction and subsequently sequestered by the late sphalerite cement. Considering that the Ga-rich sphalerite is close to the Ga-bearing coal bed of the Meiyaogou Formation, it is likely that the coal bed could be a potential source for Ga. These results highlight that tectonic deformation followed by hydrothermal fluid overprinting is favorable for the enrichment of critical metals in sphalerite-rich deposits.

Patch loss: A generic multi-scale perceptual loss for single image super-resolution

In single image super-resolution (SISR), although PSNR is a key metric for signal fidelity, images with high PSNR do not necessarily render high visual quality. As a result, current perception-driven SISR methods employ perceptual metrics close to the human eye to measure the quality of the generated images. Unfortunately, the perceptual loss and adversarial loss, widely used by the perception-driven SISR methods, still underperform on these non-differentiable perceptual metrics. To this end, we propose a generic multi-scale perceptual loss, i.e., the patch loss, which can be easily plugged into off-the-shelf SISR methods to improve a broad range of perceptual metrics. Specifically, the proposed patch loss minimizes the multi-scale similarity of image patches and enhances the restoration of regions with complex textures and sharp edges via parameter-free adaptive patch-wise attention. Our proposed patch loss introduces more realistic details compared to the perceptual loss and fewer artifacts compared to the adversarial loss.

TSDNet: A New Multiscale Texture Surface Defect Detection Model

Industrial defect detection methods based on deep learning can reduce the cost of traditional manual quality inspection, improve the accuracy and efficiency of detection, and are widely used in industrial fields. Traditional computer defect detection methods focus on manual features and require a large amount of defect data, which has some limitations. This paper proposes a texture surface defect detection method based on convolutional neural network and wavelet analysis: TSDNet. The approach combines wavelet analysis with patch extraction, which can detect and locate many defects in a complex texture background; a patch extraction method based on random windows is proposed, which can quickly and effectively extract defective patches; and a judgment strategy based on a sliding window is proposed to improve the robustness of CNN. Our method can achieve excellent detection accuracy on DAGM 2007, a micro-surface defect database and KolektorSDD dataset, and can find the defect location accurately. The results show that in the complex texture background, the method can obtain high defect detection accuracy with only a small amount of training data and can accurately locate the defect position.

Anti-drilling ability of Ziliujing conglomerate formation in Western Sichuan Basin of China

The conglomerate rock is usually featured by strong heterogeneity, high abrasiveness, and poor drillability due to its complex composition and texture, which brought a huge challenge for drilling efficiency. In order to guide the drill bit selection and high-efficiency drilling, the physical, mechanical, and drillability characteristics were investigated for conglomerate rock that collected from the lower Jurassic Ziliujing formation in the Western Sichuan Basin of China. The mineral composition, SEM micro-structure, P- and S-wave velocities, uniaxial and triaxial compressive testing, drillability, abrasiveness were systematically tested and analyzed. The mechanical properties and anti-drilling ability of Ziliujing formation were proposed for a typical deep well of S-07, and the distribution characteristics were analyzed. The results indicated that the Ziliujing rock is rich-in quartz and clay minerals, due to the co-existing of strong quartz gravel and weak argillaceous cement, the Ziliujing rock shows strong heterogeneity. The relationships are roughly linear among UCS, drillability, and grinding weight loss with P-wave velocity. The Young's modulus, UCS, internal friction angle, drillability, and abrasiveness meet the Weibull distribution pattern, while only the Poisson's ratio meets the Kernel Smooth distribution pattern. Logging interpretation results reval that the Ziliujing formation has the Young's modulus of 38.61 ± 17.08 GPa, the Poisson's ratio of 0.327 ± 0.006, the internal friction angle of 49.21 ± 11.00°, the drillability of 8.04 ± 1.54, and the abrasiveness grade of 4.32 ± 1.94. The mechanical properties and anti-drilling ability of logging interpretation are in good agreement with the experimental data. The Ziliujing formation is a kind of hard rock with strong heterogeneity, high strength, poor drillability, and medium abrasiveness. Based on the characteristics of Ziliujing formations, the SV516TAUL PDC bit with non-planar cutters was selected for the field application due to the good abrasion resistance, impact resistance, self-sharpening and thermal stability of the non-planar cutters. The field application shows that the average ROP of the new type drill bit in Ziliujing formation is 2.93 m/h, and the average footage is 225.9 m. Comparing with the traditional PDC bit, the ROP of the new drill bit with non-planar cutters has increased by 67.4%, and the footage has increased by 92.1%. The results of this paper can be utilized to guide the drill bit selection and high-efficiency drilling in conglomerate formation.