DSpace collection: 博碩士論文

針對無窮遠物體之影像式輝度計之研究;針對無窮遠物體之影像式輝度計之研究

Tue, 20 Oct 2026 07:26:35 GMT

title: 針對無窮遠物體之影像式輝度計之研究;針對無窮遠物體之影像式輝度計之研究 abstract: 本研究利用影像式輝度與色度量測系統之研究基礎，基於已完成驗證之CIE三色刺激值濾光片，進一步針對面型輝度計之建立以及灰階—輝度轉換方法進行開發與驗證。研究中利用搭載CIE XYZ三色刺激值濾光片之相機系統擷取光源影像灰階資訊，並搭配輝度計量測結果，建立灰階值與實際輝度間之對應關係，以達成由單張影像直接推估光源輝度、色度座標及相關色溫之目的。實驗架構採用具朗伯信光源特性與準直光源系統，模擬無窮遠光源，建立AR/VR近眼顯示系統之光場環境。實驗先以約±3度發散角的光源系統，驗證研究方法的可行性，再應用於±15度大角度發散角的光源系統進行研究，並透過不同曝光時間與亮度條件下之量測結果，分析相機灰階響應與輝度之線性特性、穩定性及動態範圍表現。本研究除建立灰階值與 CIE XYZ 三色刺激值間之轉換模型外，亦進一步針對大角度光源之量測需求，發展全畫面量測與多區域拼接方法。研究中利用不同視角位置之影像量測結果進行校正與拼接，藉以重建±15度範圍內之光場分佈資訊，並分析不同角度下灰階值與輝度間之對應關係。此外，針對不同曝光時間下之灰階資料進行校正分析，建立不同曝光條件間之轉換關係，以提升高亮度與低亮度區域之量測精度與適用範圍。實驗結果顯示，本研究所建立之灰階轉換模型可有效將影像灰階值轉換為實際輝度與色度參數，且與輝度計量測結果具有良好一致性；而透過全畫面量測與拼接方式，亦能有效重建大角度光源之輝度分佈。相較於傳統單點式輝度計，本研究所建立之影像式量測系統具備非接觸、高解析度、大面積同步量測及大視角量測之優勢，可有效提升量測效率並降低設備成本。未來可進一步結合角度補償與離軸校正技術，以提升面型輝度量測系統於顯示器檢測、AR/VR 光學模組、智慧照明及光場量測等應用之量測精度與實用性。;This study builds upon previous research on imaging-based luminance and chromaticity measurement systems. Based on previously validated CIE XYZ tristimulus filters， an imaging luminance measurement system and grayscale-to-luminance conversion method were further developed and experimentally verified. A camera equipped with CIE XYZ tristimulus filters was used to capture the grayscale information of the light source， and reference measurements obtained using a commercial luminance meter were used to establish the relationship between camera grayscale values and actual luminance. Through this approach， the proposed system is capable of directly estimating luminance， chromaticity coordinates， and correlated color temperature (CCT) from captured images. A light source with approximately Lambertian characteristics and a collimated optical system were employed to simulate an infinity target and establish an optical field representative of AR/VR near-eye display systems. The feasibility of the proposed method was first verified using a light source with a divergence angle of approximately ±3°， and the method was subsequently extended to a large-angle light source with a divergence angle of ±15°. Measurements under different exposure times and luminance levels were conducted to investigate the linearity， stability， and dynamic range of the camera grayscale response. In addition to establishing conversion models between grayscale values and CIE XYZ tristimulus values， this study further developed full-field measurement and multi-region image stitching methods for large-angle light sources. Measurement results obtained at different viewing angles were calibrated and stitched to reconstruct the light-field distribution over an angular range of ±15°， and the relationship between grayscale values and luminance at different viewing angles was analyzed. Furthermore， grayscale data acquired under different exposure times were calibrated to establish conversion relationships between different exposure conditions， thereby improving the measurement accuracy and applicable range for both high- and low-luminance regions. Experimental results demonstrate that the proposed grayscale conversion models can effectively convert image grayscale values into actual luminance and chromaticity parameters， showing good agreement with measurements obtained using a commercial luminance meter. The full-field measurement and image stitching methods were also capable of effectively reconstructing the luminance distribution of large-angle light sources. Compared with conventional point-by-point luminance measurement using a luminance meter， the proposed imaging system offers the advantages of non-contact measurement， high spatial resolution， full-field simultaneous acquisition， and large-field-of-view measurement， while improving measurement efficiency and reducing equipment cost. Future work will focus on incorporating angular compensation models and off-axis calibration techniques to further improve the measurement accuracy and practical applicability of the imaging luminance measurement system for display inspection， AR/VR optical modules， intelligent lighting， and light-field measurement applications.

利用散斑進行中遠距三維物體之辨識;Mid-to-Long Range Three-Dimensional Object Reconstruction Using Speckle Feature Displacement

Tue, 20 Oct 2026 07:25:59 GMT

title: 利用散斑進行中遠距三維物體之辨識;Mid-to-Long Range Three-Dimensional Object Reconstruction Using Speckle Feature Displacement abstract: 三維量測廣泛應用於工業檢測、智慧製造與自動化量測，但中遠距離條件下的投影能量、影像取樣與系統幾何仍可能限制量測品質。本研究提出以投射式雷射散斑特徵位移進行中遠距離三維物體重建與辨識的方法，並以結構光掃描點雲作為幾何參考模型。本研究以 532 nm 綠光雷射經物鏡擴束後照射擴散片形成散斑圖樣，利用二維自相關、徑向平均與半高位置量測散斑尺寸（Speckle Size），分析傳播距離與有效照明孔徑的影響。其後以 0–30 cm 多平面校正與正規化互相關（Normalized Cross-Correlation， NCC）追蹤散斑特徵，將二維位移軌跡投影至主要方向並以一階模型建立深度對應；未知物重建時，於搜尋區域（Search Area）內選取最高 NCC 位置估測高度並建立三維點雲。重建點雲三軸統一為毫米後，以 K = 16 的 K 近鄰（K-Nearest Neighbors， KNN）平均鄰近距離與中位數絕對偏差（Median Absolute Deviation， MAD）門檻移除離群點。辨識流程以快速點特徵直方圖（Fast Point Feature Histograms， FPFH）建立候選對應，經隨機抽樣一致性（RANSAC）粗配準與點對面迭代最近點（Point-to-Plane Iterative Closest Point， ICP）精配準，再以均方根誤差（Root Mean Square Error， RMSE）評估幾何差異。實驗結果顯示，散斑尺寸隨傳播距離增加而增大，並隨有效照明孔徑增加而減小；在 6 m、12 m 與 18 m 的測試配置下，六張面具皆能以最低 RMSE 正確匹配至對應參考模型。固定 12 m 時，測試範圍內較小的散斑尺寸整體上對應較低的正確配對 RMSE，顯示本方法具有應用於中遠距離三維重建與已知模型辨識的可行性。;Three-dimensional (3D) measurement is widely used in industrial inspection， intelligent manufacturing， and automated metrology， while projected optical power， image sampling， and system geometry can limit measurement quality at mid-to-long ranges. This study proposes a method for mid-to-long-range 3D object reconstruction and identification based on projected laser speckle feature displacement， with structured-light point clouds used as geometric reference models. A 532-nm green laser is expanded by a microscope objective and projected onto a diffuser to generate a speckle pattern. Speckle size is measured from the two-dimensional autocorrelation， radial average， and half-maximum position to investigate the effects of propagation distance and effective illumination aperture. Multi-plane calibration images acquired over 0–30 cm are then used to track speckle features by normalized cross-correlation (NCC). The two-dimensional displacement trajectory is projected onto its principal direction and modeled by a first-order depth relation. During reconstruction， the highest NCC within a search area surrounding the calibrated trajectory is used to estimate the feature height and construct a 3D point cloud. The reconstructed coordinates are converted to a common millimeter scale. Outliers are removed using the mean three-dimensional distance to K = 16 nearest neighbors with a threshold defined as the median plus one median absolute deviation (MAD). Fast Point Feature Histograms (FPFH) establish candidate correspondences， Random Sample Consensus (RANSAC) provides coarse registration， and Point-to-Plane Iterative Closest Point (ICP) performs fine registration. Geometric discrepancy is evaluated by the one-way nearest-neighbor root mean square error (RMSE) from the speckle-reconstructed point cloud to each structured-light reference point cloud. Experimental results show that speckle size increases with propagation distance and decreases as the effective illumination aperture increases. Under the tested 6 m， 12 m， and 18 m system configurations， all six masks are correctly matched to their corresponding reference models by selecting the lowest RMSE. At a fixed distance of 12 m， smaller speckle sizes within the tested range generally correspond to lower correct-match RMSE values. These results demonstrate the feasibility of projected speckle， multi-plane calibration， and point-cloud registration for mid-to-long-range 3D reconstruction and closed-set object identification.

五十度視角之微型化準直鏡系統設計及其幾何光學分析;Design and Geometrical Optics Analysis of a Miniaturized Collimating System with a 50-Degree Field of View

Tue, 20 Oct 2026 07:25:43 GMT

title: 五十度視角之微型化準直鏡系統設計及其幾何光學分析;Design and Geometrical Optics Analysis of a Miniaturized Collimating System with a 50-Degree Field of View abstract: 本論文旨在設計出微型化且有高影像品質的五十度視角準直鏡頭，並分析其中相關之幾何光學理論。本文選用0.32"的OLED面板，解析度為800×600，像素尺寸為8.1 μm，對應62 lp/mm。本研究設計的準直鏡頭特點為體積小於1 c.c.的同時，能維持其MTF在62 lp/mm 時大於0.78，在250 lp/mm時大於0.33。而且光學畸變小於0.11%，電視畸變與橫向色差皆小於人眼的分辨率1角分，相對照度達到65%以上。因為有一定的影像品質，同時也有把光線準直化、體積小的性質，所以此鏡頭適用於AR系統，讓使用者能長時間觀看清晰的影像，又不會因為其體積而造成配戴上的負擔。本論文的設計由四片非球面透鏡以及一片平板保護玻璃組成。四片非球面透鏡可使用塑膠或玻璃製造，而在公差範圍內分別可達到的極限解像度，在220 lp/mm時大於0.110，對應像素尺寸為2.273 μm；玻璃版本則是在260 lp/mm時大於0.105，對應像素尺寸為1.923 μm。因此，在對解析度要求不高的情況下塑膠版本成本較低，而在高空間頻率上有要求的情況下，則玻璃版本的公差控制成本較低。另外，塑膠和玻璃兩個版本的準直鏡頭皆適用於對角半長度為4.05 mm的4：3和16：9面板。;This study aims to design a miniaturized collimating lens with a 50-degree field of view and high image quality， and to analyze the relevant theories of geometrical optics. In this study， a 0.32" OLED microdisplay with an 800×600 resolution and a pixel size of 8.1 μm (corresponding to 62 lp/mm) was chosen. The collimating lens designed in this study features a compact volume of less than 1 c.c. while maintaining a MTF of over 0.78 at 62 lp/mm and over 0.33 at 250 lp/mm. Furthermore， the optical distortion is less than 0.11%， both TV distortion and lateral chromatic aberration are within the human eye′s resolution limit of 1 arcminute， and the relative illumination exceeds 65%. Combining high image quality， light collimation， and a compact form factor， this lens is highly suitable for AR systems， allowing users to view clear images for extended periods without bearing a heavy wearing burden due to its size. The design consists of 4 aspherical lenses and a flat glass plate. The 4 aspherical lenses can be manufactured using either plastic or glass. Within tolerance limits， the resolution limit for the plastic version exceeds 0.110 at 220 lp/mm， corresponding to a pixel size of 2.273 μm. For the glass version， the limit exceeds 0.105 at 260 lp/mm， corresponding to a pixel size of 1.923 μm. Consequently， the plastic version offers a lower manufacturing cost when resolution requirements are modest， whereas the glass version provides a lower tolerance control cost for applications demanding high spatial frequencies. Additionally， both the plastic and glass versions of the collimating lens are compatible with 4:3 and 16:9 microdisplays with a diagonal half-length of 4.05 mm.

三乘三微影光型縫合之研究;三乘三微影光型縫合之研究

Tue, 20 Oct 2026 07:25:31 GMT

title: 三乘三微影光型縫合之研究;三乘三微影光型縫合之研究 abstract: 在半導體製程中，以紫外光來進行微影與固化是不可或缺的技術，為達到高良率的製程，曝光機構的輸出光型需達到高均勻度、特定尺寸及準直角之嚴格限制，因此光學系統設計及元件加工面臨高度的挑戰性。此外，隨著大尺寸晶圓製程技術的發展，大面積的曝光之需求日益增加，因此，為避免直接加大元件尺寸增加系統設計的複雜度，以及元件製程的昂貴，本論文提出以數個相同曝光機組合進行「光型疊加」的方式來拓展曝光面積，驗證開發具備擴展性的 UV-LED 曝光系統的可行性，藉此達成降低開發成本並滿足大面積曝光之需求。因應產業需求，我們希望開發出的曝光機具有曝光面積約為 600 × 600 mm² 之矩形均勻光型、其最低照度大於 20 mW/cm²、不均勻度低於 5%、且工作距離 (Working Distance， WD) 需小於 500 mm。首先，我們針對單一曝光機中各元件配置及系統參數，包括：紫外光源、聚光透鏡、透鏡陣列、工作距離…等參數進行探討其對光型品質之影響；其次，我們以此光學系統為出發點，組合3 x 3個曝光機，來疊加縫合9個光型以滿足曝光面積要求，同時，我們進行元件與系統參數優化，配合縫合機制尋求最佳配置，來提升整體光型的均勻度以及光學利用率。在工作距離為495 mm的條件下，我們可以完成曝光面積為 629 × 629 mm²，不均勻度為12.2 %，且最低照度為 22 mW/cm² 的光型設計，其效能與目標有所差距，但若將工作距離小幅放寬至615 mm，則不均勻度可有效降至為4.7 %，且最低照度提升到 29.2 mW/cm²，面積為570 × 570 mm²，更接近目標光型的均勻度要求。這些成果表示，我們提出的光型疊加技術加上以此進行系統參數的調整，確實能同時考量實際製程能力與工業規格要求，讓大面積曝光機的規格達到產業界應用之需求，為低成本、大面積之光學曝光機具提供具競爭力之解決方案。;Ultraviolet (UV) lithography and curing are essential technologies in semiconductor manufacturing. To achieve high process yield， an exposure system must provide high illumination uniformity， a specified exposure area， and a well-controlled collimation angle. As wafer sizes continue to increase， the demand for large-area exposure has grown significantly. Enlarging optical components， however， increases both system complexity and manufacturing cost. This study proposes a light-pattern stitching method that combines multiple identical UV-LED exposure modules to expand the effective exposure area， providing a scalable and cost-effective solution for large-area exposure applications. According to industrial specifications， the proposed exposure system is expected to provide a uniform rectangular illumination field of approximately 600 × 600 mm²， with an irradiance greater than 20 mW/cm²， a non-uniformity below 5%， and a working distance (WD) shorter than 500 mm. A single exposure module was first designed by investigating the effects of key optical parameters， including the UV light source， condenser lens， lens array， and working distance. Subsequently， a 3 × 3 array of exposure modules was employed to stitch nine illumination patterns together. System parameters were further optimized to improve illumination uniformity and optical efficiency while meeting the required exposure area. At a working distance of 495 mm， the proposed system achieved an exposure area of 629 × 629 mm²， a minimum irradiance of 22 mW/cm²， and a non-uniformity of 12.2%. By increasing the working distance to 615 mm， the non-uniformity was reduced to 4.7%， while the minimum irradiance increased to 29.2 mW/cm²， the exposure area of 570 × 570 mm². These results demonstrate that the proposed light-pattern stitching technique effectively enables scalable， low-cost， large-area UV exposure while satisfying industrial performance requirements. In conclusion， this study first designs a rectangular light field with high uniformity and subsequently utilizes light pattern superposition techniques alongside dynamic system parameter adjustments. It provides a competitive solution for the development of low-cost， large-area optical exposure systems.