Visual Quality Research Articles

No-Reference Image Quality Assessment Algorithm

The presented article focuses on the development of a local image quality assessment algorithm, specifically designed for analyzing contrast and overall visual data quality. The proposed algorithm aims to enhance the efficiency of image assessment, particularly in conditions of low contrast and the presence of various types of noise. The algorithm's methodology takes into account spectral ranges and provides precise local contrast assessment, making it applicable to a broad spectrum of tasks related to image analysis and enhancement. The developed approach has the potential to improve the quality of visual data by supporting crucial aspects of contrast perception and overall image quality.

Clinical profile, visual outcome and quality of life in patients undergoing pan retinal photocoagulation for proliferative diabetic retinopathy

Introduction Visual outcomes and quality of life of individuals with proliferative diabetic retinopathy following pan-retinal photocoagulation (PRP) have only been briefly documented in a few publications. Improved quality of life experienced by patients as a result of PRP is directly associated with a positive impact on visual outcomes. Aim To determine whether visual outcomes and quality of life after PRP in diabetic patients would result in a better predictive image of the patient as a whole, thus boosting the success rates and efficacy of this treatment method. Methods P.R.P. was performed under topical anesthesia as defined by the early treatment diabetic retinopathy study (E.T.D.R.S.) guidelines. Conclusion This evidence-based analytical observational prospective study could aid in exploring the prognostic value of pan-retinal photocoagulation in proliferative diabetic retinopathy.

Impact of Aspheric Monofocal Intraocular Lens Implantation on Uncorrected Intermediate Visual Acuity: a Combined Analysis.

To evaluate binocular intermediate visual acuity (IVA), depth of focus, and other visual outcomes achieved with a monofocal aspheric intraocular lens (IOL) using pooled data from 2 randomized, double-masked, controlled trials. The studies conducted at 32 sites included patients aged ≥22 years with bilateral cataracts, preoperative corneal astigmatism 1.0 D, and lens power 18.0-25.0 D. Patients received bilateral AcrySof IQ IOLs (SN60WF). Primary endpoint data were collected at month 6. Binocular uncorrected and corrected distance visual acuity (UDVA and CDVA) at 4 m, binocular uncorrected and corrected IVA (UIVA and DCIVA) at 66 cm, manifest refraction spherical equivalent (MRSE), and binocular defocus curve at 4 m were assessed under photopic conditions. Validated questionnaires were used to assess spectacle use and quality of vision. Of 233 patients who received SN60WF, 228 had visual acuity data at 6 months. Under photopic conditions, 51% of the eyes had pupils >4 mm, 40% had pupils 3-4 mm, and 9% had pupils <3 mm. Mean ± SD UDVA and CDVA were -0.019 ± 0.110 and -0.088 ± 0.082 logMAR, respectively. Mean ± SD UIVA and DCIVA were 0.125 ± 0.145 and 0.196 ± 0.139 logMAR, respectively. UIVA and DCIVA of 20/32 or better were achieved by 83% (188/228) and 71% (162/228) of patients, respectively. Mean ± SD MRSE was -0.007 ± 0.404 D for the first eye and 0.036 ± 0.371 for the second eye. The defocus curve demonstrated binocular vision of 0.24 logMAR or better from +1.2 to -1.5 D. Spectacle independence for distance and intermediate vision was reported by 86% and 41% of the patients, respectively. Based on questionnaires, 61%, 79%, and 65% of the patients did not experience starbursts, halos, or glare. A monofocal aspheric IOL (SN60WF) assessed in a large, pooled study provided excellent distance vision and clinically functional intermediate vision.

Oculopalatal Tremor: A Narrative Review of Pathophysiology, Clinical Presentation, and Management Strategy

Abstract Oculopalatal tremor (OPT) is a complex neurological disorder characterized by acquired oscillatory nystagmus synchronized with tremors of the soft palate and other muscles. The article discusses the pathology, clinical manifestations, and diagnostic methods of OPT. A comprehensive literature search was conducted in PubMed and Google Scholar using keywords and relevant articles were studied and analysis was done. Vertical pendular nystagmus is the hallmark, while other muscles such as the neck, head, larynx, and diaphragm may be affected. The pathophysiology is due to lesions of the Guillain–Mollaret triangle (GMT), which causes hypertrophy of the inferior olivary. Neuroimaging reveals hypertrophy of the inferior olivary medulla, which aids in diagnosis. Drug treatments such as gabapentin and memantine can reduce nystagmus, although the visual quality may not permanently improve. The study explores the complexity of the pathophysiology and clinical presentation of OPT. New treatments that target abnormal neuronal connections with drugs such as quinine or mefloquine are being investigated. The potential of deep brain stimulation (DBS) remains uncertain, with promising aspects but limited efficacy. A synergy of technology and treatment is proposed to advance OPT treatment. Future studies will aim to clarify the nuances of responses to OPT and may include a comparative study of medication and DBS. OPT is mainly caused by a disruption in GMT/dentato-rubro-olivary pathway, presenting with tremor, and nystagmus is diagnosed with magnetic resonance imaging. Gabapentin and memantine have proved to be effective in improving the condition except for visual changes.

S‐LASSIE: Structure and smoothness enhanced learning from sparse image ensemble for 3D articulated shape reconstruction

AbstractIn computer vision, the task of 3D reconstruction from monocular sparse images poses significant challenges, particularly in the field of animal modelling. The diverse morphology of animals, their varied postures, and the variable conditions of image acquisition significantly complicate the task of accurately reconstructing their 3D shape and pose from a monocular image. To address these complexities, we propose S‐LASSIE, a novel technique for 3D reconstruction of quadrupeds from monocular sparse images. It requires only 10–30 images of similar breeds for training. To effectively mitigate depth ambiguities inherent in monocular reconstructions, S‐LASSIE employs a multi‐angle projection loss function. In addition, our approach, which involves fusion and smoothing of bone structures, resolves issues related to disjointed topological structures and uneven connections at junctions, resulting in 3D models with comprehensive topologies and improved visual fidelity. Our extensive experiments on the Pascal‐Part and LASSIE datasets demonstrate significant improvements in keypoint transfer, overall 2D IOU and visual quality, with an average keypoint transfer and overall 2D IOU of 59.6% and 86.3%, respectively, which are superior to existing techniques in the field.

Adaptive HEVC video steganograhpy based on PU partition modes

High EfficiencyVideoCoding (HEVC) −based steganography has gained attention as a prominent research focus. Especially, block structure based HEVC video steganography has received increasing attention due to commendable performance. However, current block structure- based steganography algorithms confront with challenges such as reduced coding efficiency and limited capacity. To avoid these problems, an adaptive video steganography algorithm based on Prediction Unit (PU) partition mode in I-frames is proposed. This is done through the analysis of the block division process and the visual distortion resulting from the modification of the PU partition mode in HEVC. The PU block structure is utilized as steganographic covers, and the Rate Distortion Optimization (RDO) technique is introduced to establish an adaptive distortion function for Syndrome-trellis code (STC). Further comparison is performed between the proposed method and the state-of-the-art steganography algorithms, confirming its advantages in embedding capacity, compression efficiency, visual quality, and resistance to video steganalysis.

A Two-Level Security Layer for Medical Data

Implementing a two-level security approach comprising cryptography and steganography in Electronic Health Record (EHR) systems ensures comprehensive protection of sensitive patient information. Cryptography encryption methods alone may not provide adequate protection, as they can be susceptible to attacks and also, steganography, has the visual quality issues after embedding. The combination of RSA cryptography and DWT steganography will offers a comprehensive solution for securing medical data, ensuring confidentiality, integrity, and compliance with privacy regulations, while DWT steganography provides covert embedding within medical images, preserving diagnostic integrity and enhancing data protection. In this paper, a secure two-level layer of medical data security is proposed to encrypt secret information using Rivest-Shamir-Adleman (RSA) while the encrypted secret information is embedded using Discrete Wavelet Transform (DWT). The performance of the proposed method was evaluated using Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR) and Normalized Cross-Correlation (NCC) metrics. The results obtained show that our method performs with a value of 0.105 for MSE, 49.713 for PSNR and 0.912 for NCC showing high visual quality and low imperceptibility.

Fuzzy-driven image enhancement via ABR-fractal-fractional differentiation

Low-light images often suffer from low sharpness and low contrast, hindering their visual quality and the performance of computer vision systems. To address this issue, we propose a novel image enhancement algorithm that combines local detail enhancement and global contrast enhancement. Our algorithm first transforms the crisp image into an intuitionistic fuzzy image. Next, we construct a global adaptive brightness transformation membership function to generate the first enhanced image. The second enhanced image is obtained using a newly proposed fractal-fractional differential operator. Finally, an image fusion technique is employed to effectively extract image features and integrate the locally and globally enhanced images. Our proposed technique effectively enhances the quality of low-light images while preserving their unique characteristics. Experimental results demonstrate that our method achieves comparable or even superior performance compared to state-of-the-art approaches, both qualitatively and quantitatively.

Local Means Binary Networks for Image Super-Resolution.

The success of modern single image super-resolution (SISR) algorithms is inspired by the development of deep convolutional neural networks (CNNs). However, these CNN-based methods require considerable computation and complexity, making it impossible for these methods to perform real-time calculations in edge devices. Thus, lightweight model design has become a development trend in the super-resolution field, including pruning, quantization, and other methods. The 1-bit quantization is an extreme lightweight method which can reduce the calculation amount of the model in an extreme manner and is friendly to hardware such as edge devices. Most existing binary quantization approaches lead to a large information loss during forward propagation, especially in detailed color information (e.g., edge, texture, and contrast). The loss of color information makes modern binary methods unsuitable for SISR tasks. We think the loss occurs because these methods typically utilize a uniform threshold to quantize the weights and activations. Thus, in this article, we thoroughly analyze the difference between normal classification tasks and SISR tasks, and present a binarization scheme based on local means. The proposed method can maintain more detailed information in feature maps using dynamic thresholds during quantization. Specifically, each value in the full precision activations has a corresponding threshold during the quantization process, and those thresholds are determined by the full precision values of the surroundings. In addition, a gradient approximator is introduced to adaptively optimize the gradient for updating binary weights. We then verify the effectiveness of our method for training binary networks on several SISR benchmarks including VDSR and SRResNet. Experimental results show that the proposed method can outperform the state-of-the-art algorithms to obtain binary networks for image super-resolution with better peak signal-to-noise ratio (PSNR) values and visual quality.

Multi-scale recurrent attention gated fusion network for single image dehazing

The purpose of single image dehazing is to eliminate the bad influence of haze on images, so as to maintain more scene information of images. In recent years, the convolutional neural networks (CNN) have made significant contributions to single image dehazing. However, the visual quality of dehazed images still needs to be further improved. In view of the problems of single-scale shallow image feature extraction and the insufficient use of intermediate layer features in existing dehazing networks, we propose an end-to-end Multi-scale Recurrent Attention Gated Fusion Network (MRAGFN) to address the image dehazing task. We cascade three Dual Attention Fusion (DAF) modules to progressively form three haze-relevant features map, meanwhile, we adopt downsampling operation on the input to produce global feature map, which are used to weight the three feature maps to compensate for the missing of single-scale feature information. We present Feature Enhancement Module (FEM) to enhance the feature representation ability of these weighted feature maps. We design Recurrent Attention Gated Fusion (RAGF) module by adding attention mechanism and gating mechanism to gradually obtain more refined features based on these weighted features while eliminating redundant features. Experimental results on different hazy images demonstrate that the proposed dehazing network can restore the haze-free images and perform better than the state-of-the-art dehazing networks in terms of the objective indicators (such as PSNR, SSIM)and the subjective visual quality.

Robotization of the IR-Thermographic technique – impact on the visualisation quality and considerations on the data workflow

Quality control automation is becoming increasingly popular in industrial production lines. Active thermography techniques are well-regarded for their adaptability, providing fast, non-contact, and full-field non-destructive evaluation. Automating thermographic evaluation can increase assessment speed and repeatability without sacrificing inspection accuracy. By using a robot arm to manipulate the thermographic setup, it becomes possible to inspect large components and refine scans on suspicious zones, even in parts with complex geometries. In this study, the performance of a new thermographic inspection platform is compared with a conventional setup to showcase the potential improvements. A plastic curved-shaped sample with artificial flat bottom hole defects is used as a benchmark for the comparison. The advantages and disadvantages of robotizing the infrared non-destructive setup are analyzed, and the impact of the data workflow and future research activities are also discussed.

A Visualization and Radiation Treatment Plan Quality Scoring Method for Triage in a Population-Based Context

PurposeTo develop a clinically intuitive and easily understandable scoring method using statistical metrics to visually determine the quality of a radiation treatment plan. Methods and MaterialsData from 111 head and neck cancer patients were used to establish a percentile-based scoring system for treatment plan quality evaluation on both a plan-by-plan and objective-by-objective basis. The percentile scores for each clinical objective and the overall treatment plan score were then visualized using a daisy plot. To validate our scoring method, 6 physicians were recruited to assess 60 plans each using a scoring table consisting of a 5-point Likert scale (with scores ≥3 considered passing). Spearman correlation analysis was conducted to assess the association between increasing treatment plan percentile rank and physician rating, with Likert scores of 1 and 2 representing clinically unacceptable plans, scores of 3 and 4 representing plans needing minor edits, and a score of 5 representing clinically acceptable plans. Receiver operating characteristic curve analysis was used to assess the scoring system's ability to quantify plan quality. ResultsOf the 60 plans scored by the physicians, 8 were deemed as clinically acceptable; these plans had an 89.0th ± 14.5 percentile value using our scoring system. The plans needing minor edits or deemed unacceptable had more variation, with scores falling in the 62.6th ± 25.1 percentile and 35.6th ± 25.7 percentile, respectively. The estimated Spearman correlation coefficient between the physician score and treatment plan percentile was 0.53 (P < .001), indicating a moderate but statistically significant correlation. Receiver operating characteristic curve analysis demonstrated discernment between acceptable and unacceptable plan quality, with an area under the curve of 0.76. ConclusionsOur scoring system correlates with physician ratings while providing intuitive visual feedback for identifying good treatment plan quality, thereby indicating its utility in the quality assurance process.

Effect of X-ray Irradiation and Carnauba Wax Coating on Quality of Lime (Citrus latifolia Tan.) Fruit

The quality of Persian (Tahiti) lime (Citrus latifolia Tan.) fruit was determined following coating with carnauba wax and X-ray irradiation at doses suitable for disinfestation of quarantine pests. Fruit with or without carnauba wax coating were treated with irradiation doses of 0, 150, 300, or 450 Gy, and stored for 14 days at 13 °C and 6 days at 20 °C to simulate commercial transportation and marketing conditions from Hawaii to the continental United States. The fruit color, weight loss, total soluble solids (TSS) content, and titratable acidity (TA) were analyzed at 7, 14, and 14 + 6 days post irradiation. Wax coating significantly delayed fruit peel discoloration, and reduced fruit weight loss by more than 7% compared with the unwaxed controls. Irradiation did not affect ΔE of the peel for coated fruit at day 14 + 6. Irradiation with or without coating did not affect ΔE of flesh color, weight loss, TSS content, or TA. Wax coating combined with irradiation treatment of limes at doses ≤450 Gy ensured marketable visual quality and chemical composition while providing quarantine security.

Identification of Circular Patterns in Capsule Endoscopy Bubble Frames.

A significant number of frames captured by the wireless capsule endoscopy are involved with varying amounts of bubbles. Whereas different studies have considered bubbles as nonuseful agents due to the fact that they reduce the visualization quality of the small intestine mucosa, this research aims to develop a practical way of assessing the rheological capability of the circular bubbles as a suggestion for future clinical diagnostic purposes. From the Kvasir-capsule endoscopy dataset, frames with varying levels of bubble engagements were chosen in two categories based on bubble size. Border reflections are present on the edges of round-shaped bubbles in their boundaries, and in the frequency domain, high-frequency bands correspond to these edges in the spatial domain. The first step is about high-pass filtering of border reflections using wavelet transform (WT) and Differential of Gaussian, and the second step is related to applying the Fast Circlet Transform (FCT) and the Hough transform as circle detection tools on extracted borders and evaluating the distribution and abundance of all bubbles with the variety of radii. Border's extraction using WT as a preprocessing approach makes it easier for circle detection tool for better concentration on high-frequency circular patterns. Consequently, applying FCT with predefined parameters can specify the variety and range of radius and the abundance for all bubbles in an image. The overall discrimination factor (ODF) of 15.01, and 7.1 showing distinct bubble distributions in the gastrointestinal (GI) tract. The discrimination in ODF from datasets 1-2 suggests a relationship between the rheological properties of bubbles and their coverage area plus their abundance, highlighting the WT and FCT performance in determining bubbles' distributions for diagnostic objectives. The implementation of an object-oriented attitude in gastrointestinal analysis makes it intelligible for gastroenterologists to approximate the constituent features of intra-intestinal fluids. this can't be evaluated until the bubbles are considered as non-useful agents. The obtained results from the datasets proved that the difference between the calculated ODF can be used as an indicator for the quality estimation of intraintestinal fluids' rheological features like viscosity, which helps gastroenterologists evaluate the quality of patient digestion.

Data Hiding Methods Using Voting Strategy and Mapping Table

&lt;p&gt;With advancements in technology, the study of data hiding (DH) in images has become more and more important. In this paper, we introduce a novel data hiding scheme that employs a voting strategy to predict pixels based on their neighbors, then embeds data into the predicted pixels according to a designed mapping table. To extract the information, it is only necessary to use the voting strategy to predict the pixels again, then to compare the predicted and hidden pixels to extract the secret data with the assistance of the mapping table. Our experimental results demonstrate that the proposed hiding scheme has a high embedding capacity, and preserves a satisfactory visual quality. Additionally, it attains a high peak signal-to-noise ratio (PSNR) even at high embedding capacity.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt;

Varied Attributes of Jalapeño Pepper Cultivars Influence Fresh-cut Product Quality

During the past 40 years, the US fresh-cut product market has experienced a consistent increase in demand because consumers prioritize health and convenience. Increased interest in fresh-cut products and ready-to-eat vegetables has led to innovations in breeding, product selection, and packaging. However, despite the increased popularity of bell pepper and chile pepper (Capsicum annuum L.), research of fresh-cut jalapeño pepper is limited. This study was conducted to identify jalapeño cultivars that could be suitable as a raw fresh-cut product and explore measures beyond tissue membrane electrolyte leakage (EL) of processed products that may be useful for the identification of cultivars suitable for fresh-cut applications. A total of 22 fresh-cut parameters were examined across five cultivars of jalapeño peppers and 10 intercrosses of these cultivars, including visual quality based on an image analysis via a computer vision system, package headspace gas composition, tissue membrane EL, and texture. Based on our results, the genotypes were grouped into five clusters using a cluster analysis. Variables including tissue softening (r2 = 0.95), EL (r2 = 0.95), total energy of the mesocarp (r2 = 0.95), and package headspace carbon dioxide (CO2) partial pressure (r2 = 0.94) had strong associations with the cluster. A principal component analysis with biplots further confirmed the results. Cultivars Goliath and Emerald Fire and their hybrids in the first and second clusters showed good quality for fresh-cut applications. The fifth cluster, represented by a single cultivar, Jalapeño M, had the smallest physical size, rapid shelf-life decline, accumulated CO2 partial pressures, increased EL, and rapid tissue softening in comparison with the other genotypes. All jalapeño cultivars except Jalapeño M maintained good quality until day 14 postprocessing, and some maintained good quality until 21 days postprocessing. Hybrid crosses suggested that two of the cultivars evaluated, Goliath and Emerald Fire, were useful as parents when transferring superior fresh-cut quality traits to progeny. Traditionally, the EL level has been used as an index of freshness (or tissue deterioration). Our results showed that other quality analyses, including measurements of tissue softening via an imaging analysis, and physical analyses of tissue firmness can also be used as indices for the freshness of fresh-cut jalapeños. The results suggest that fruit size, wall thickness, and skin toughness might be useful as predictive measures in the field for the selection of jalapeño genotypes with superior fresh-cut quality.

GAN‐Based Multi‐Decomposition Photo Cartoonization

AbstractBackgroundCartoon images play a vital role in film production, scientific and educational animation, video games, and other fields, and are one of the key visual expressions of artistic creation. However, since hand‐crafted cartoon images often require a great deal of time and effort on the part of professional artists, it is necessary to be able to automatically transform real‐world images into different styles of cartoon images. Although cartoon images vary from artist to artist, cartoon images generally have the unique characteristics of being highly simplified and abstract, with clear edges, smooth color shading, and relatively simple textures. However, existing image cartoonization methods tend to create a number of problems when performing style transfer, which mainly include: (1) the resulting generated images do not have obvious cartoon‐style textures; and (2) the generated images are prone to structural confusion, color artifacts, and loss of the original image content. Therefore, it is also a great challenge in the field of image cartoonization to be able to make a good balance between style transfer and content keeping.MethodsIn this paper, we propose a GAN‐based multi‐attention mechanism for image cartoonization to address the above issues. The method combines the residual block used to extract deep network features in the generator with the attention mechanism, and further strengthens the perceptual ability of the generative model to cartoon images through the adaptive feature correction of the attention module to improve the cartoon features of the generated images. At the same time, we also introduce the attention mechanism in the convolution block of the discriminator, which is used to further reduce the image visual quality problem caused by the style transfer process. By introducing the attention mechanism into the generator and discriminator models of the generative adversarial network, our method enables the generated images to have obvious cartoon‐style features while effectively improving the image's visual quality.ResultsA large number of quantitative, qualitative, and ablation experiments are conducted to demonstrate the advantages of our method in the field of image cartoonization and the role of each module in the method.

NeRF-NQA: No-Reference Quality Assessment for Scenes Generated by NeRF and Neural View Synthesis Methods.

Neural View Synthesis (NVS) has demonstrated efficacy in generating high-fidelity dense viewpoint videos using a image set with sparse views. However, existing quality assessment methods like PSNR, SSIM, and LPIPS are not tailored for the scenes with dense viewpoints synthesized by NVS and NeRF variants, thus, they often fall short in capturing the perceptual quality, including spatial and angular aspects of NVS-synthesized scenes. Furthermore, the lack of dense ground truth views makes the full reference quality assessment on NVS-synthesized scenes challenging. For instance, datasets such as LLFF provide only sparse images, insufficient for complete full-reference assessments. To address the issues above, we propose NeRF-NQA, the first no-reference quality assessment method for densely-observed scenes synthesized from the NVS and NeRF variants. NeRF-NQA employs a joint quality assessment strategy, integrating both viewwise and pointwise approaches, to evaluate the quality of NVS-generated scenes. The viewwise approach assesses the spatial quality of each individual synthesized view and the overall inter-views consistency, while the pointwise approach focuses on the angular qualities of scene surface points and their compound inter-point quality. Extensive evaluations are conducted to compare NeRF-NQA with 23 mainstream visual quality assessment methods (from fields of image, video, and light-field assessment). The results demonstrate NeRF-NQA outperforms the existing assessment methods significantly and it shows substantial superiority on assessing NVS-synthesized scenes without references. An implementation of this paper are available at https://github.com/VincentQQu/NeRF-NQA.

Tolerância à salinidade e respostas espectrais foliares em mudas de quatro espécies ornamentais herbáceas

ABSTRACT Studies on using brackish water for the irrigation of ornamental species are still scarce, mainly considering qualitative aspects of the plants. Therefore, the present study aimed to identify salt tolerance and characterize leaf spectral responses of herbaceous ornamental species at the stage of commercial seedling production. The research was carried out from December 2020 to February 2021, under greenhouse conditions, in Fortaleza - Ceará, Brazil. The experiment was conducted in a randomized block design with split plots, with main plots consisting of irrigation-water salinity levels (0.5, 2.0, 4.0, 6.0, and 8.0 dS m-1), and subplots by the species Catharanthus roseus, Celosia cristata, Celosia plumosa, and Chrysanthemum coronarium, with four replications. The evaluation parameters were dry mass production, visual sensory analysis, salt tolerance, and leaf spectral responses. Plant visual quality was maintained up to 2.0 dS m-1 for Chrysanthemum coronarium and 4.0 dS m-1 for Celosia cristata, Celosia plumosa, and Catharanthus roseus, which were classified as moderately tolerant at those respective salinity levels. Salinity caused noticeable changes in leaf spectral responses, especially in the visible region.

DCID: A divide and conquer approach to solving the trade-off problem between artifacts caused by enhancement procedure in image downscaling

Conventional research on image downscaling is conducted to improve the visual quality of the resultant downscaled image. However, there is an intractable problem, a trade-off relationship between artifacts such as aliasing and ringing, caused by enhancement procedure in image downscaling. To solve this problem, we propose a novel method that applies a divide-and-conquer approach for image downscaling (DCID). Specifically, the proposed DCID includes Weight-Net for dividing regions into enhancement first and artifact-least first regions and two generators that are optimized for divided regions to conquer the trade-off problem in the image downscaling task. The proposed method can generate a downscaled image without creating artifacts while preserving the perceptual quality of the input image. In objective and subjective evaluations, our experimental results show that the quality of the downscaled images generated by the proposed DCID is significantly better than benchmark methods.