首页 | 本学科首页   官方微博 | 高级检索  
文章检索
  按 检索   检索词:      
出版年份:   被引次数:   他引次数: 提示:输入*表示无穷大
  收费全文   44456篇
  免费   10157篇
  国内免费   5247篇
电工技术   1827篇
综合类   5376篇
化学工业   910篇
金属工艺   743篇
机械仪表   3874篇
建筑科学   1149篇
矿业工程   541篇
能源动力   286篇
轻工业   1099篇
水利工程   312篇
石油天然气   429篇
武器工业   531篇
无线电   11917篇
一般工业技术   3862篇
冶金工业   638篇
原子能技术   221篇
自动化技术   26145篇
  2025年   100篇
  2024年   1287篇
  2023年   1336篇
  2022年   1711篇
  2021年   2063篇
  2020年   1956篇
  2019年   1633篇
  2018年   1458篇
  2017年   1769篇
  2016年   1935篇
  2015年   2316篇
  2014年   3014篇
  2013年   2887篇
  2012年   3663篇
  2011年   3721篇
  2010年   3242篇
  2009年   3217篇
  2008年   3439篇
  2007年   3521篇
  2006年   2875篇
  2005年   2555篇
  2004年   2047篇
  2003年   1624篇
  2002年   1260篇
  2001年   1021篇
  2000年   782篇
  1999年   603篇
  1998年   479篇
  1997年   438篇
  1996年   338篇
  1995年   262篇
  1994年   226篇
  1993年   190篇
  1992年   152篇
  1991年   117篇
  1990年   114篇
  1989年   79篇
  1988年   69篇
  1987年   47篇
  1986年   52篇
  1985年   50篇
  1984年   38篇
  1983年   41篇
  1982年   28篇
  1981年   19篇
  1980年   9篇
  1979年   12篇
  1976年   8篇
  1975年   8篇
  1959年   6篇
排序方式: 共有10000条查询结果,搜索用时 15 毫秒
951.
    
There exist few studies investigating the multi-query image retrieval problem. Existing methods are not based on hash codes. As a result, they are not efficient and fast. In this study, we develop an efficient and fast multi-query image retrieval method when the queries are related to more than one semantic. Image hash codes are generated by a deep hashing method. Consequently, the method requires lower storage space, and it is faster compared to the existing methods. The retrieval is based on the Pareto front method. Reranking performed on the retrieved images by using non-binary deep-convolutional features increase retrieval accuracy considerably. Unlike previous studies, the method supports an arbitrary number of queries. It outperforms similar multi-query image retrieval studies in terms of retrieval time and retrieval accuracy.  相似文献   
952.
    
Aiming at the problem of distortion of dark channel algorithm in defogging the sky region,an improved image defogging algorithm based on the guided filtering and adaptive tolerance mechanism was proposed.Firstly,the fitted transmissivity graphs were calculated for the windows with different sizes.Then,the transmissivity was further refined by the guided filtering technique.After that,the transmissivity in sky area was revised by an adaptive tolerance mechanism.Finally,the restored image was converted from RGB space to HSV space,and thus the brightness and contrast of the images could be color compensated.Experimental results show that the proposed algorithm restores the images effectively and obtain preferable defogging results with regard to the processing of bright areas such as the sky areas.  相似文献   
953.
    
In this article, we present an evaluation method for the skin color distribution in the face area. Unlike previous methods that extract a specific area, our method subdivides the entire face into small regions and analyzes detailed, per-frame textures. Our evaluation method for skin color distribution is based on facial feature points and includes segmentation that takes into account the facial skeleton and muscle orientation. The use of facial feature points enables a comparison at relatively equal positions on the face without depending on the shape or size of the individual's face. Our evaluation method is versatile, and as an application, we clarified age-specific features and seasonal variations of facial color distribution. As a result of applying this evaluation method to the facial images of women aged 20 to 78 years, we confirmed that the lightness of the face decreased as age increased. In particular, the decrease in lightness was remarkable in the region along the cheekbone, from the temple to the center of the cheek. Furthermore, we analyzed the seasonal changes of melanin distribution in the face area. This showed that the melanin index increased particularly in the cheekbone area in the summer when the influence of ultraviolet rays became large. Our novel methodology and the data presented in this article will be useful in various fields, such as dermatology, cosmetics, and computer vision.  相似文献   
954.
    
When users select products, they consider the emotional experience resulting from the color of the product. However, the emotional demands of users for product color are multidimensional and diverse. It is very important yet difficult to accurately grasp multiemotional image requirements and effectively convert them into design elements. Therefore, multiemotional product color design (MEPCD) has become a very important and challenging research topic. In this article, a novel MEPCD system using gray theory (GT) and nondominated sorting genetic algorithm-III (NSGA-III) is proposed to effectively solve the MEPCD problem. First, the image perception spaces of users, which exist in different emotional dimensions, were collected using factor analysis and the semantic differential technique. Then, GT was used to establish a multidimensional emotional product color image evaluation model. Finally, NSGA-III was used to optimize and design a multiemotional color scheme for a product. Furthermore, according to actual conditions, an MEPCD system was established based on the proposed method. The design case study shows that the method and design system proposed in this article have a certain range of applicability and can effectively improve the practicality of MEPCD.  相似文献   
955.
    
A method to obtain the impact strength of triple-base gun propellant is proposed according to strain energy density. Using a drop-weight impact testing machine, the impact strengths of DAGR125-21/19 gun propellant at room temperature (20 °C) and low temperature (−40 °C) were studied. In the experiments, there were different impact energies via changing the drop weight or height. The surface images of gun propellants during the impact process were captured using a high-speed camera. The deformation of DAGR125-21/19 gun propellant was calculated through digital image correlation method (DICM). After analyzing the surface images and deformation, it was found that there was a good agreement between the maximum of axial nominal strain energy density (ANSED) and initial fracture point. Finally, the impact strength of DAGR125-21/19 gun propellant was obtained through calculating the strain energy density during the plastic stage between the yield and initial fracture points. Moreover, successive parallel and replication experiment results proved the rationality and feasibility of the proposed method to determine the impact strengths of DAGR125-21/19 gun propellant at room temperature (20 °C) and low temperature (−40 °C).  相似文献   
956.
为了提高分类性能和运算效率,提出结合结构特征与梯度特征的图像哈希算法. 该算法对输入图像进行预处理提高算法的鲁棒性,将预处理后的图像转换到YCbCr颜色空间,提取亮度Y分量. 利用Y分量的峰顶曲线和峰谷曲线来获取外部结构特征,同时提取峰顶和峰谷的位置信息来构建内部结构特征. 结合外部结构特征和内部结构特征得到图像的结构特征;提取Y分量的横向梯度与纵向梯度来构建图像的梯度特征;将结构特征与梯度特征联合起来并扰乱得到最终的哈希序列. 实验结果表明,所提算法对亮度调整、对比度调整和高斯低通滤波等保持内容的图像处理较稳健. 与已有算法对比,该算法具有更好的受试者工作特性(ROC)曲线和较好的图像分类性能,在篡改检测实验中,该算法可以有效地检测篡改图像.  相似文献   
957.
提出一种基于贝叶斯概率模型的泊松噪声图像去噪方法. 该方法基于贝叶斯最大后验概率模型框架,结合泊松概率分布,构建图像去噪模型. 考虑到马尔科夫随机场不能对复杂自然图像有效表征,引入高阶的马尔科夫专家场作为模型先验正则项,以表征图像自身概率分布. 利用二次惩罚函数,优化求解去噪模型,还原清晰图像. 将所提方法与其他去噪算法进行仿真实验对比,并采用峰值信噪比和结构相似性2种评价指标对去噪效果进行客观评价. 实验结果表明:与传统去噪方法相比,该方法的峰值信噪比至少提升了0.18 dB,去噪性能显著优于其他方法,能更好地保留图像的细节信息.  相似文献   
958.
应用当前较新颖且分类性能靠前的卷积神经网络Xception作为基础网络结构,尝试采用多尺度的深度可分离卷积来提升模型特征信息的丰富度,在模型中嵌入SE-Net模块增强有用特征通道,减弱无用特征通道. 实验结果表明:提出的多尺度SE-Xception模型在2种噪声程度不同的服装数据集中均取得不错表现;ACS数据集的平均分类准确率为78.34%,分别高于VGG-16、ResNet-50和Xception模型8.52%、4.81%、3.69%;验证了多尺度SE-Xception模型具有更好的特征提取能力,能够提取到更多的服装信息,从而提高服装图像分类效果,一定程度上解决了特征尺度单一、信息丰富度低的问题.  相似文献   
959.
为了弥补传统测量手段在监测桥梁整体变形和长期实时监测的不足,克服基于单目视觉的数字摄影技术无法监测桥梁三维变形的缺陷,提出图像匹配-时间基线视差法。在适当位置布设观测站,架设数码相机,在距离数码相机不远处布设参考点组成参考平面,使得参考平面与摄影方向垂直,在桥梁上布设观测点。根据图像匹配-时间基线视差法求得变形点在物平面上的二维变形值,再利用三维变形监测原理将物平面上的水平变形分解到沿桥梁方向和垂直于桥梁方向,从而求得桥梁的三维变形。结果表明:桥梁变形点的监测精度在物平面上的X方向上为0.72 mm,在Z方向上为1.16 mm,能够满足变形监测的精度要求。凤凰山路桥在X, Y, Z以及综合方向上都表现出较好的弹性,且最大的正负挠度的绝对值之和为7.57 mm≈(1/8)×(L/1000)(桥梁挠度的容许变形),桥梁的健康状态良好。桥梁监测及预警系统能够实现数据获取、传输、存储、处理,以及结果展示一体化,且变形曲线图能够直观展示桥梁结构的变形走向,有效的预警潜在的危险。  相似文献   
960.
为了解决现有基于深度学习方法的视觉情感分析忽略了图像各局部区域情感呈现的强度差异问题,提出一种结合空间注意力的卷积神经网络spatial attention with CNN, SA-CNN用于提升视觉情感分析效果。设计一个情感区域探测神经网络用于发现图像中诱发情感的局部区域;通过空间注意力机制对情感映射中各个位置赋予注意力权重,恰当抽取各区域的情感特征表示,从而有助于利用局部区域情感信息进行分类;整合局部区域特征和整体图像特征形成情感判别性视觉特征,并用于训练视觉情感的神经网络分类器。该方法在3个真实数据集TwitterⅠ、TwitterⅡ和Flickr上的情感分类准确率分别达到82.56%、80.23%、79.17%,证明利用好图像局部区域情感表达的差异性,能提升视觉情感分类效果。  相似文献   
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号